We are seeking an experienced, hands-on Senior AI Engineer to join the Generative AI applications Platform group and lead the backend implementation and architecture of AI/LLM solutions – from agent graphs and tooling to RAG, streaming, and production deployment.
As a Senior AI Engineer you will
Design and own agent architectures – Build and evolve graph-based agent workflows (multi-node LLM flows, tool execution, routing, human-in-the-loop review gates) using LangGraph, with clear state schemas, checkpointing, and streaming to production.
Turn product and user needs into backend AI – Work with Engineers, Product, and Analysts to translate business problems into technical requirements and implementations, including agent types, tools, RAG pipelines, and configuration-driven behavior.
Design, develop, and deploy GenAI capabilities end-to-end – LangChain tools and integrations, RAG (retrievers, vector stores, agentic flows), structured outputs, and APIs for chat, Copilot-style integrations, and MCP.
Raise the bar on quality and reliability – Establish patterns for observability (e.g., LangSmith), error handling, content safety, bounded autonomy (tool schemas, review workflows), and evaluation systems so that AI behavior is predictable and auditable.
Mentor and align the team – Provide technical guidance on LLM backend architecture and LangGraph/LangChain best practices so the team can iterate quickly and safely.
As a Senior AI Engineer you will
Design and own agent architectures – Build and evolve graph-based agent workflows (multi-node LLM flows, tool execution, routing, human-in-the-loop review gates) using LangGraph, with clear state schemas, checkpointing, and streaming to production.
Turn product and user needs into backend AI – Work with Engineers, Product, and Analysts to translate business problems into technical requirements and implementations, including agent types, tools, RAG pipelines, and configuration-driven behavior.
Design, develop, and deploy GenAI capabilities end-to-end – LangChain tools and integrations, RAG (retrievers, vector stores, agentic flows), structured outputs, and APIs for chat, Copilot-style integrations, and MCP.
Raise the bar on quality and reliability – Establish patterns for observability (e.g., LangSmith), error handling, content safety, bounded autonomy (tool schemas, review workflows), and evaluation systems so that AI behavior is predictable and auditable.
Mentor and align the team – Provide technical guidance on LLM backend architecture and LangGraph/LangChain best practices so the team can iterate quickly and safely.
Requirements:
Backend-LLM & agent architecture – 5+ years in production ML/AI and backend systems; recent hands-on experience with backend LLM systems, including agent workflows (e.g., LangGraph or similar), LangChain tooling and chains, state management, and streaming (e.g., SSE). You think in terms of nodes, state schemas, routing, and human-in-the-loop.
Technical stack – Proficient in Python; comfortable with LangGraph, LangChain, FastAPI, PostgreSQL, and optionally Azure AI Search or similar. Experience with LLM providers (OpenAI/Azure, Google Vertex AI, etc.) and RAG (retrievers, chunking, reranking) expected.
Generative AI in production – Proven track record building production GenAI applications, including multi-step agents, RAG, tool-augmented LLMs, and ideally human-in-the-loop or review flows. You care about observability, validation, and safe rollout.
Bachelor's degree or higher in Computer Science or a related field, and strong communication and collaboration skills.
Backend-LLM & agent architecture – 5+ years in production ML/AI and backend systems; recent hands-on experience with backend LLM systems, including agent workflows (e.g., LangGraph or similar), LangChain tooling and chains, state management, and streaming (e.g., SSE). You think in terms of nodes, state schemas, routing, and human-in-the-loop.
Technical stack – Proficient in Python; comfortable with LangGraph, LangChain, FastAPI, PostgreSQL, and optionally Azure AI Search or similar. Experience with LLM providers (OpenAI/Azure, Google Vertex AI, etc.) and RAG (retrievers, chunking, reranking) expected.
Generative AI in production – Proven track record building production GenAI applications, including multi-step agents, RAG, tool-augmented LLMs, and ideally human-in-the-loop or review flows. You care about observability, validation, and safe rollout.
Bachelor's degree or higher in Computer Science or a related field, and strong communication and collaboration skills.
This position is open to all candidates.
