Senior AI Engineer

• Enterprise Orchestration: Build and scale complex workflows using n8n (Vertex AI Pipelines experience is an advantage), ensuring seamless integration between LLMs (Gemini 2.5/3.0), internal systems and databases, and external APIs
• Modern AI Deployment: Containerize and deploy models as scalable microservices using FastAPI, Docker, and GKE (Google Kubernetes Engine)
• Advanced AI Orchestration: Design and implement sophisticated LLM workflows and multi-agent systems, potentially adopting frameworks like LangGraph, LangChain, AgentSkills, and MCP to create autonomous, tool-using solutions
• End-to-End Agentic RAG Development: Lead the complete RAG lifecycle, managing everything from data cleansing, chunking, and embedding strategies to the final delivery of production-ready enterprise solutions
• Model Optimization: Fine-tune Large Language Models (LLMs) and Small Language Models (SLMs like Gemma 3) using PEFT (LoRA/QLoRA) within Vertex AI Studio
• Prompt Engineering: Develop and refine high-quality prompts to assist in the precise execution and optimization of AI solution logic
• Market Intelligence: Maintain a proactive watch on the AI market to identify and adopt emerging technologies that provide a competitive advantage
• Production Quality & Ops: Collaborate with MLOps/LLMOps teams to ensure seamless product delivery, implementing robust monitoring to maintain high production quality after go-live
• Collaborative Solution Design: Work closely with the High-Code Engineering team and engage directly with business stakeholders to gather requirements and ensure AI solutions are perfectly aligned with user needs
• Model Strategy & Evaluation: Perform rigorous model evaluations to decide which LLMs should be adopted or replaced within existing solutions to optimize performance and cost
• User Interface Hosting: Host user interfaces with Gradio/Streamlit for users to interact with AI solutions

• Vertex AI Suite: Hands-on experience with Vertex AI Agent Builder, Model Garden, and Vertex AI Search & Conversation
• Gemini Ecosystem: Proficiency in utilizing the Gemini API (Pro, Flash, and Ultra) and Gemini Code Assist for accelerated development
• Data Cleansing & Analytics: Hands-on experience in data cleansing with Python for grounding AI solutions in structured data
• Agentic Frameworks: Expertise in LangGraph and LangChain for building stateful, multi-turn agentic applications
• Model Engineering: Strong proficiency in Python (PyTorch, Scikit-learn, TensorFlow) for training, fine-tuning, and evaluating neural networks
• Cloud: Proven experience with and a deep understanding of the Azure and GCP ecosystems
• CI/CD/MLOps: Mastery of Vertex AI Pipelines, Azure DevOps, Argo Workflows, and container orchestration via Kubernetes (GKE)
• Orchestration Tools: Expert-level knowledge of n8n, specifically using Python Code Nodes and custom API connectors
• Real-time Data: Experience with CDC to ensure vector stores reflect real-time database changes
• Experience building large-scale production AI workloads on Azure or Google Cloud

Related AI Engineering certifications are beneficial