Senior AI Product Engineer – Agentic Systems

About the role

If you've ever shipped an agent that worked great in a demo but fell apart in production, this role fixes that for real clients at scale. As a Senior AI Product Engineer you will own the reasoning core of the empower platform, shaping agent orchestration, prompt architecture, and evaluation systems that turn agentic behavior into trusted automation.

Key responsibilities

• Design and implement multi‑agent workflows and orchestration graphs using LangGraph.
• Apply DSPy or comparable declarative prompt‑programming to create systematic, testable prompts.
• Build and maintain evaluation harnesses tracked in MLflow to measure accuracy, hallucination rate, latency and instruction‑following.
• Architect agent memory, tool‑calling, guardrails and human‑in‑the‑loop controls for production client decisions.
• Prototype retrieval architectures on top of the Neo4j‑backed Business Knowledge Graph in partnership with Level I engineers.

Required profile

• Demonstrated agency – the ability to spot gaps, define goals and drive solutions without waiting for direction.
• Systemic thinking – understanding how changes to retrieval, ontology or agent policies affect the whole platform and client outcomes.
• Structured communication for AI‑directed work – writing clear specifications and delegating tasks to both humans and AI coding agents.

Required skills

• Python programming (primary language for AI‑adjacent work).
• Experience with LangGraph or comparable agent‑orchestration frameworks.
• Proficiency in DSPy or similar declarative prompt‑programming tools.
• Knowledge of LlamaIndex (or other RAG frameworks) and retrieval pipelines using PostgreSQL with pgvector and pg_search.
• Hands‑on work with Neo4j (Cypher queries) and graph‑based knowledge representation.
• Use of MLflow for experiment tracking and evaluation.
• Cloud‑native deployment experience (Azure preferred, AWS/GCP transferable), containerization and CI/CD pipelines.
• Integration of LLM APIs (Anthropic, OpenAI, vLLM, Ollama) into production services.
• Daily use of AI coding agents such as Claude Code, Cursor, GitHub Copilot or Codex for scaffolding and testing.