This list contains only the countries for which job offers have been published in the selected language (e.g., in the French version, only job offers written in French are displayed, and in the English version, only those in English).
We’re looking for a Senior Backend Engineer to join our newly formed AI R&D pod—a small, fast-moving team dedicated to building the future of AI-native product experiences at Posh. This is a backend-focused role with a strong emphasis on systems architecture and AI implementation. You will be responsible for building the intelligent, scalable, and reliable systems that power our AI features. Your work will focus on designing and deploying sophisticated Multi-Agent Systems, moving beyond simple RAG to create truly autonomous and helpful user experiences. You’ll work closely with frontend engineers and product designers to bring cutting-edge AI tools to our platform. Expect to build robust APIs, architect data flows for evaluations and fine-tuning, and pioneer new ways to leverage AI within our existing infrastructure. This represents a unique opportunity to build the foundational backend of our AI products, with the chance to ship experimental features to a large, growing, and highly engaged user base.
Job Responsibility:
Build and Scale AI Services: Design, build, and maintain scalable backend services and APIs for AI-powered features, writing primary production code in Python
Architect Multi-Agent Systems: Move beyond standard RAG to design and implement complex, hierarchical Multi-Agent Systems that can perform sophisticated, multi-step tasks
Implement Evaluation and Fine-Tuning: Build robust frameworks to evaluate the quality of AI systems and manage fine-tuning pipelines to continuously improve model performance
Own Cloud Infrastructure with IaC: Define, deploy, and manage our AI infrastructure using Terraform. You'll be responsible for scaling our container-based serverless solutions while ensuring reliability and performance
Optimize for Efficiency: Deeply analyze the tradeoffs between model performance, latency, and cost to make pragmatic, business-aware technical decisions when using managed AI services
Integrate Across the Stack: Collaborate with our core engineering teams by occasionally working in TypeScript (Node.js) to integrate AI features into our main application
Requirements:
3–6+ years of backend or full-stack engineering experience, with a proven track record of shipping high-quality, scalable systems in fast-paced environments
Deep expertise in Python and its ecosystem for web services and data processing
Strong experience with Infrastructure as Code (Terraform), a major cloud platform (e.g., GCP, AWS, Azure), and deploying containerized applications
A passion for shaping 0→1 products in a lean, fast-paced R&D environment where you'll help define new playbooks for AI-native experiences
Nice to have:
Pragmatic AI/ML Exposure: Familiarity with managed AI services (e.g., Vertex AI, AWS Bedrock), working with LLMs, or building advanced AI systems is a plus. Experience with model evaluation frameworks (e.g., RAGAs, LangSmith, DeepEval) or fine-tuning is helpful but not required. The ability to think about tradeoffs between cost, latency, and performance is valuable
Experience with open-source agentic frameworks (e.g., LangGraph, CrewAI, Strands, etc) is a plus
Experience with MLOps, data engineering, or a background in consumer, marketplace, or event-driven platforms
What we offer:
Health,Dental and Vision Insurance
Equinox Membership
Unlimited PTO
Team Events, Dinners, & Offsites, Free Event Tickets to Dope Shows
New MacBook
Daily Uber Eats Credit
Relocation bonuses are available for some out-of-state candidates