CrawlJobs Logo

Model Optimization Engineer

AMD

Location Icon

Location:
China, Beijing

Category Icon
Category:
IT - Software Development

Job Type Icon

Contract Type:
Not provided

Salary Icon

Salary:

Not provided
Save Job
Save Icon
Apply Position

Job Description:

We are looking for a hands‑on Engineer to design, implement, and optimize AI model training and inference solutions for AMD platforms. The role focuses on end‑to‑end performance and accuracy improvements at the framework, model, and operator levels, with strong emphasis on low‑bitwidth quantization, model compression, and real‑world deployment. You will work closely with AMD hardware and software teams, support customers, and contribute to open‑source projects and inference/training frameworks.

Job Responsibility:

  • Design, implement, and optimize inference and training pipelines for AMD GPUs/accelerators at the framework, model, and operator levels
  • Lead research and development of model optimization algorithms: low‑bitwidth quantization, pruning/sparsity, compression, efficient attention mechanisms, and lightweight architectures
  • Implement and tune CUDA/ROCm/Triton kernels for critical operators
  • profile and eliminate performance bottlenecks
  • Integrate and optimize models for PyTorch/JAX and common distributed training/inference stacks (Torchtitan, Megatron, DeepSpeed, HF Transformers, etc.)
  • Reduce latency and increase throughput for large‑model inference (e.g., batching strategies, caching, speculative decoding)
  • Contribute to and/or maintain open‑source inference/training tools, ensuring production readiness and community adoption
  • Provide technical support and guidance to customers and internal teams to achieve target accuracy and performance on AMD platforms

Requirements:

  • Strong software engineering in Python and C/C++
  • Practical experience with PyTorch/JAX and building/extending deep learning frameworks
  • Hands‑on CUDA and/or ROCm development
  • experience writing or optimizing GPU kernels
  • Experience with Triton (kernel development/optimization) is highly desired
  • Proven experience with model optimization techniques, especially low‑bitwidth quantization and other compression methods
  • Familiarity with GenAI inference engines and optimizations (e.g., vLLM, SGLang, xDiT, continuous batching, speculative decoding)
  • Skilled at profiling and performance debugging across stack layers (operator → model → framework → hardware)

Nice to have:

  • Publications or contributions in model optimization / ML systems are a strong plus
  • Experience with distributed training/inference frameworks (e.g., Torchtitan, Megatron, DeepSpeed, HF Accelerate, vLLM, SGLang, xDiT)
  • Background in PTQ/QAT quantization algorithms, efficient attention variants, or low-bitwidth/sparse kernels
  • Familiarity with real‑world deployment constraints and performance validation

Additional Information:

Job Posted:
December 17, 2025

Icon
View All Jobs In This Company
Job Link Share:
Copy Link Icon
Facebook Icon Twitter Icon LinkedIn Icon

Looking for more opportunities? Search for other job offers that match your skills and interests.

Briefcase Icon

Similar Jobs for Model Optimization Engineer

Senior Aerodynamics Modeling and Optimization Engineer

Archer is an aerospace company based in San Jose, California building an all-ele...
Location
Location
United States , San Jose
Salary
Salary:
Not provided
archer.com Logo
Archer Aviation
Expiration Date
Until further notice
Flip Icon
Requirements
Requirements
  • BS / MS / PhD in Aerospace Engineering or a related field
  • 4+ years of experience with BS, or 3+ years of experience with MS, or 1+ years of experience with PhD modeling rotorcraft, tiltrotor, eVTOL aerodynamics at full-vehicle level
  • Strong understanding of fundamentals of fixed-wing and rotorcraft aerodynamics, performance, stability & control
  • Experience in eVTOL and/or multicopter vehicle aerodynamics design and analysis, including 6 DoF vehicle trimming and trajectory optimization
  • Experience with gradient-based and gradient-free optimization techniques
  • Experience with surrogate modeling techniques (like Kriging methods) and statistical analysis
  • Experience with experimental data processing and reduction techniques
  • Proficiency in Python programming
  • Experience with software development, object-oriented, version control best practices, as well as Git, CICD, Conda
  • Excellent work planning and issue resolution skills
Job Responsibility
Job Responsibility
  • Perform low/mid/high fidelity aerodynamic simulations of Archer eVTOL aircraft
  • Develop linear/non-linear aerodynamic models to predict aircraft behavior and performance throughout the flight envelope
  • Analyze experimental data (either from flight test or wind tunnel) to identify sources of model errors, validate, and improve aerodynamic models of the vehicle
  • Develop efficient methods to feed flight test data back into aerodynamic simulation models of various fidelity and complexity
  • Contribute to the development of Archer aerodynamic software stack, improving methods and workflows
  • Coordinate with other cross-functional teams and pilots for flight simulator aerodynamic modeling updates and issue resolution
  • Fulltime
Read More
Arrow Right

Sr. Aerodynamics Engineer, Modeling and Simulation

Archer is an aerospace company based in San Jose, California building an all-ele...
Location
Location
United States , San Jose
Salary
Salary:
150000.00 - 190000.00 USD / Year
archer.com Logo
Archer Aviation
Expiration Date
Until further notice
Flip Icon
Requirements
Requirements
  • BS / MS / PhD in Aerospace Engineering or a related field
  • 4+ years of experience with BS, or 3+ years of experience with MS, or 1+ years of experience with PhD modeling rotorcraft, tiltrotor, eVTOL aerodynamics at full-vehicle level
  • Strong understanding of fundamentals of fixed-wing and rotorcraft aerodynamics, performance, stability & control
  • Experience in eVTOL and/or multicopter vehicle aerodynamics design and analysis, including 6 DoF vehicle trimming and trajectory optimization
  • Experience with gradient-based and gradient-free optimization techniques
  • Experience with surrogate modeling techniques (like Kriging methods) and statistical analysis
  • Experience with experimental data processing and reduction techniques
  • Proficiency in Python programming
  • Experience with software development, object-oriented, version control best practices, as well as Git, CICD, Conda
  • Excellent work planning and issue resolution skills
Job Responsibility
Job Responsibility
  • Perform low/mid/high fidelity aerodynamic simulations of Archer eVTOL aircraft
  • Develop linear/non-linear aerodynamic models to predict aircraft behavior and performance throughout the flight envelope
  • Analyze experimental data (either from flight test or wind tunnel) to identify sources of model errors, validate, and improve aerodynamic models of the vehicle
  • Develop efficient methods to feed flight test data back into aerodynamic simulation models of various fidelity and complexity
  • Contribute to the development of Archer aerodynamic software stack, improving methods and workflows
  • Coordinate with other cross-functional teams and pilots for flight simulator aerodynamic modeling updates and issue resolution
  • Fulltime
Read More
Arrow Right

Research Engineer, World Models

You will build large multi-modal generative “world models” that predict future s...
Location
Location
United States , Palo Alto
Salary
Salary:
180000.00 - 300000.00 USD / Year
1x.tech Logo
1X Technologies
Expiration Date
Until further notice
Flip Icon
Requirements
Requirements
  • Strong experience with Python (and related tooling such as Bazel)
  • Proficiency with PyTorch or equivalent deep learning frameworks
  • Familiarity with simulation platforms (e.g., Isaac Sim, MuJoCo)
  • Experience building or working with multi-modal generative models combining video, audio, text, and action prediction
  • Ability to design and optimize large-scale data pipelines and loaders for training
  • Understanding of scaling laws and metrics for foundation models
Job Responsibility
Job Responsibility
  • Full-stack engineering: data engineering, model architecture design, and delivering polished products
  • Develop high-throughput data loaders for large multi-modal datasets
  • Implement tokenizers and transformers tailored for web-scale robot data
  • Translate improvements in world model architectures into improvements in robot autonomy
  • Predict how real-world robot performance scales with pre-training metrics (e.g., log loss)
What we offer
What we offer
  • Health, dental, and vision insurance
  • 401(k) with company match
  • Paid time off and holidays
  • Fulltime
Read More
Arrow Right

Senior Software Engineer – ML Model Compliance & Automation

We are seeking a highly skilled and motivated Senior Software Engineer to lead t...
Location
Location
India , Jaipur
Salary
Salary:
Not provided
infoobjects.com Logo
InfoObjects
Expiration Date
Until further notice
Flip Icon
Requirements
Requirements
  • Experience Required: 3 - 7 yrs
  • GoLang (preferred)
  • Python (preferred)
  • Bash
  • MLOps Tools: KitOps, MLModelCI, MLflow, ONNX, TensorFlow, PyTorch, Docker
  • SBOM & Security: Syft, Grype, Trivy, CycloneDX, SPDX
  • CI/CD: GitHub Actions, GitLab CI, Jenkins, ArgoCD
  • Infra: Kubernetes, Docker, Helm, Terraform
  • Cloud: AWS, GCP, Azure (EKS/GKE/ECS preferred)
  • Version Control: Git, GitOps
Job Responsibility
Job Responsibility
  • Model Packaging & Artifact Management: Design and implement workflows for packaging ML models using KitOps, ONNX, MLflow, or TensorFlow SavedModel
  • Manage model artifact versioning, registries, and reproducibility
  • Ensure artifact integrity, consistency, and traceability across CI/CD pipelines
  • Model Profiling & Optimization: Automate model profiling (latency, size, ops) using MLModelCI, TorchServe, or ONNX Runtime
  • Apply quantization, pruning, and format conversions (e.g., FP32→INT8) for optimization
  • Embed profiling and optimization checks into CI/CD pipelines to assess deployment readiness
  • Compliance & SBOM Generation: Develop pipelines to generate and validate SBOMs for ML models
  • Implement compliance checks for licensing, vulnerabilities, and security using CycloneDX, SPDX, Syft, or Trivy
  • Validate schema, dependencies, and runtime environments for production readiness
  • Cloud Integration & Deployment: Automate model registration, endpoint creation, and monitoring setup in AWS/GCP/Azure
  • Fulltime
Read More
Arrow Right
New

Autonomy Engineer - Deep Learning Model Acceleration

Learning a semantic and geometric understanding of the world from visual data is...
Location
Location
Switzerland , Zurich
Salary
Salary:
Not provided
skydio.com Logo
Skydio
Expiration Date
Until further notice
Flip Icon
Requirements
Requirements
  • Demonstrated hands-on experience with MLOps, ML inference acceleration/optimization, and edge deployment
  • Strong knowledge of DL fundamentals, techniques, and state-of-the-art DL models/architectures
  • Strong fundamentals in CV, image processing, and video processing
  • Demonstrated hands-on experience building and managing ML pipelines for solving vision or vision language tasks including data preparation, model training, model deployment, and monitoring
  • Experience and understanding of security and compliance requirements in ML infrastructure
  • Experience with ML frameworks and libraries
  • Demonstrated ability to take a concept and systematically drive it through the software lifecycle: architecture, development, testing, deployment, and monitoring
  • Comfortable navigating and delivering within a complex codebase
  • Strong communication skills and the ability to collaborate effectively at all levels of technical depth
Job Responsibility
Job Responsibility
  • Develop solutions for high-performance deep learning inference for CV workloads that can deliver high throughput and low latency on different hardware platforms
  • Profile CV and Vision Language Models (VLMs) to analyze performance, identify bottlenecks and acceleration/optimization opportunities and improve power efficiency of deep learning inference workloads
  • Design and implement end to end MLOps workflows for model deployment, monitoring, and re-training
  • Utilize advanced Machine Learning knowledge to leverage training or runtime frameworks or model efficiency tools to improve system performance
  • Create new methods for improving training efficiency
  • Implement GPU kernels for custom architectures and optimized inference
  • Design and implement SDKs that allow customers/external developers to create autonomous workflows using Machine Learning (ML)
  • Leverage your expertise and best-practices to uphold and improve Skydio’s engineering standards
What we offer
What we offer
  • Competitive base salaries
  • Equity in the form of stock options
  • Comprehensive benefits packages
  • Relocation assistance may also be provided for eligible roles
  • Group health insurance plans
  • Paid vacation time
  • Sick leave
  • Holiday pay
  • Retirement savings plan
  • Fulltime
Read More
Arrow Right
New

Autonomy Engineer - Deep Learning Model Acceleration

Learning a semantic and geometric understanding of the world from visual data is...
Location
Location
United States , San Mateo
Salary
Salary:
170000.00 - 277500.00 USD / Year
skydio.com Logo
Skydio
Expiration Date
Until further notice
Flip Icon
Requirements
Requirements
  • Demonstrated hands-on experience with MLOps, ML inference acceleration/optimization, and edge deployment
  • Strong knowledge of DL fundamentals, techniques, and state-of-the-art DL models/architectures
  • Strong fundamentals in CV, image processing, and video processing
  • Demonstrated hands-on experience building and managing ML pipelines for solving vision or vision language tasks including data preparation, model training, model deployment, and monitoring
  • Experience and understanding of security and compliance requirements in ML infrastructure
  • Experience with ML frameworks and libraries
  • Demonstrated ability to take a concept and systematically drive it through the software lifecycle: architecture, development, testing, and deployment, and monitoring
  • Comfortable navigating and delivering within a complex codebase
  • Strong communication skills and the ability to collaborate effectively at all levels of technical depth
Job Responsibility
Job Responsibility
  • Develop solutions for high-performance deep learning inference for CV workloads that can deliver high throughput and low latency on different hardware platforms
  • Profile CV and Vision Language Models (VLMs) to analyze performance, identify bottlenecks and acceleration/optimization opportunities and improve power efficiency of deep learning inference workloads
  • Design and implement end to end MLOps workflows for model deployment, monitoring, and re-training
  • Utilize advanced Machine Learning knowledge to leverage training or runtime frameworks or model efficiency tools to improve system performance
  • Create new methods for improving training efficiency
  • Implement GPU kernels for custom architectures and optimized inference
  • Design and implement SDKs that allow customers/external developers to create autonomous workflows using Machine Learning (ML)
  • Leverage your expertise and best-practices to uphold and improve Skydio’s engineering standards
What we offer
What we offer
  • Equity in the form of stock options
  • Comprehensive benefits packages
  • Relocation assistance may also be provided for eligible roles
  • Paid vacation time
  • Sick leave
  • Holiday pay
  • 401K savings plan
  • Group health insurance plans
  • Fulltime
Read More
Arrow Right

Senior Principal Machine Learning Engineer - LLM Post-Training and Optimization

Atlassian is seeking a highly skilled and experienced Senior Principle Machine L...
Location
Location
United States , Mountain View
Salary
Salary:
243100.00 - 407200.00 USD / Year
https://www.atlassian.com Logo
Atlassian
Expiration Date
Until further notice
Flip Icon
Requirements
Requirements
  • Ph.D. or Master’s degree in Computer Science, Machine Learning, Artificial Intelligence, or a related field
  • 8+ years of experience in machine learning, with a focus on large-scale model development and optimization
  • Deep expertise in LLM and transformer architectures (e.g., GPT, BERT, T5)
  • Strong proficiency in Python and ML frameworks such as PyTorch, JAX, or TensorFlow
  • Experience with distributed training techniques and large-scale data processing pipelines
  • Proven track record of deploying machine learning models in production environments
  • Familiarity with model optimization techniques, including quantization, pruning, and knowledge distillation
  • Strong problem-solving skills and ability to work in a fast-paced, collaborative environment
  • Excellent communication skills and ability to translate technical concepts for diverse audiences
Job Responsibility
Job Responsibility
  • Lead the fine-tuning and post-training optimization of large language models (LLMs) for diverse applications
  • Develop and implement techniques for model compression, quantization, pruning, and knowledge distillation to optimize performance and reduce computational costs
  • Conduct research on advanced techniques in transfer learning, reinforcement learning, and prompt engineering for LLMs
  • Design and execute rigorous benchmarking and evaluation frameworks to assess model performance across multiple dimensions
  • Collaborate with infrastructure teams to optimize LLM deployment pipelines, ensuring scalability and efficiency in production environments
  • Stay at the forefront of advancements in LLM technologies, sharing insights, driving innovation within the team, and leading agile development
  • Mentoring other team members, facilitating within/across team workshops, fostering a culture of technical excellence and continuous learning
What we offer
What we offer
  • health coverage
  • paid volunteer days
  • wellness resources
  • Fulltime
Read More
Arrow Right

Director - Power Grid Modeling

We are seeking a Director - Power Grid Modeling to play a key role in the techni...
Location
Location
Canada , Montréal
Salary
Salary:
Not provided
artelys.com Logo
Artelys
Expiration Date
Until further notice
Flip Icon
Requirements
Requirements
  • Engineering degree, Master’s, or PhD in energy, applied mathematics, or equivalent field, with expertise in power grid and energy systems analysis
  • Minimum of 8 years experience in the energy sector, including technical project management and business development
  • Proven experience as project manager, including team leadership
  • Strong expertise in modeling and optimization methods for power and energy systems
  • Solid knowledge of North American electricity markets, energy policies, and regulations (e.g., FERC, NERC)
  • Experience in algorithm design and software development (e.g., Python, C++, Java)
  • Excellent communication, analytical, and synthesis skills, both oral and written
  • Bilingual proficiency in French and English (minimum C1 in both languages)
  • Rigor, leadership, listening skills, and initiative
Job Responsibility
Job Responsibility
  • Lead projects from A to Z: from needs analysis and planning to budget monitoring, risk management, and deadlines
  • Ensure smooth communication with stakeholders while guaranteeing the quality and timely delivery of project outputs
  • Supervise, motivate, and develop a team of engineers and analysts in energy modeling
  • Foster your team’s skills development, ensuring a collaborative and innovative work environment
  • Coordinate human resources for project execution while optimizing their allocation
  • Implement Artelys Canada’s business development strategy in the North American power grid sector by identifying new business opportunities
  • Identify, prospect, and respond to tenders to acquire new clients
  • Leverage and expand your network to create strategic partnerships and strengthen Artelys Canada’s market presence
  • Present Artelys Canada’s innovative solutions to clients to help them tackle their challenges in energy optimization and power grid modeling
  • Maintain strong client relationships, anticipate needs, and adjust solutions to meet their requirements
What we offer
What we offer
  • Up to 3 days of remote work per week possible
  • Flexible working hours (40h/week)
  • Offices located in the city center of Montreal
  • Fulltime
Read More
Arrow Right
Welcome to CrawlJobs.com –
Your Global Job Discovery Platform
At CrawlJobs.com, we simplify finding your next career opportunity by bringing job listings directly to you from all corners of the web. Using cutting-edge AI and web-crawling technologies, we gather and curate job offers from various sources across the globe, ensuring you have access to the most up-to-date job listings in one place.
Jobs by Category
Art and Entertainment Jobs Banking Jobs Call Center Jobs Construction Jobs Consulting Jobs Customer Service Jobs Education Jobs Energy Jobs Finance Jobs Gastronomy Jobs Health and Beauty Jobs Hospitality and Tourism Jobs Human Resources Jobs Insurance Jobs IT - Administration Jobs IT - Software Development Jobs Legal Jobs Logistics Jobs Manufacturing Jobs Marketing, Digital Marketing, SEO, SEM Jobs Media Jobs Nursing Jobs Office Administration Jobs Pharmacy Jobs Physical Work Jobs Public Relations Jobs Public Sector Jobs Purchasing Jobs Quality Control Jobs Real Estate Jobs Research and Development Jobs Sales Jobs
Job Positions Jobs by Country
United States Jobs United Kingdom Jobs India Jobs Australia Jobs Canada Jobs Poland Jobs Ireland Jobs Spain Jobs
Company
Blog About Us Contact
Follow Us
Facebook
X (Twitter)
LinkedIn
Instagram
© 2025 CrawlJobs Ltd. All Rights Reserved
Terms & Conditions Privacy Policy