AI Tech Lead – Agentic Systems & RAG

About the role

Have you built agentic systems that run in production, not just in a notebook or IDE? We're looking for a hands‑on AI architect to lead the build of an enterprise agentic AI platform. You'll architect and build a server‑side agentic platform that helps business analysts, developers, and QA engineers work faster: orchestrated agents, human‑in‑the‑loop workflows in a web app, and RAG that understands both documents and source code to deliver impact and technical analysis.

Key responsibilities

• Define the architecture and pick the right approach per use case: headless CLI agents, custom orchestration, or managed cloud services (e.g., AWS Bedrock / AgentCore).
• Build agent workflows with human‑in‑the‑loop checkpoints.
• Build RAG pipelines over documents and code, using AST parsing, embeddings, vector and graph databases.
• Design short‑ and long‑term memory and context management for agents.
• Ship production Java and Python services connected to LLMs.
• Set technical standards and mentor engineers.

Required profile

• Proven hands‑on experience building production agentic systems on servers.
• Deep RAG experience: chunking, indexing, embeddings, search ranking.
• Code‑aware RAG: AST parsing with Tree‑sitter or similar.
• Graph database and vector database experience.
• Strong Java and Python expertise.
• Experience with LangGraph, LangChain or similar; headless CLI agents; GitHub Copilot SDK or equivalents.
• Confidence making and explaining architecture trade‑offs to senior stakeholders.

Required skills

• Java
• Python
• AWS Bedrock
• AgentCore
• Tree‑sitter (AST parsing)
• Graph databases
• Vector databases
• LangGraph
• LangChain
• GitHub Copilot SDK
• Angular (nice to have)

What we offer

• Opportunity to work on bleeding‑edge projects.
• Work with a highly motivated and dedicated team.
• Competitive salary.
• Flexible schedule.
• Benefits package – medical insurance, sports.
• Corporate social events.
• Professional development opportunities.
• Well‑equipped office.