What You’ll Do
- Build agent planners, tool-call flows, and structured state machines using LangGraph or similar frameworks
- Design schemas, action adapters, and cross-tool interfaces that enable deterministic, traceable LLM tool execution
- Implement robust execution logic: retries, rollbacks, timeouts, checkpointing, and replay mechanisms
- Design agent workflows with clear validation, stopping criteria, and failure handling
What We’re Looking For
- Strong experience building agent systems, LLM tool-calling pipelines, or orchestration frameworks
- Deep intuition for schemas, action abstractions, state representation, and reproducibility
- Ability to reason rigorously about system-level failure modes, edge cases, and safe tool interaction
Why This Role
- Build agent systems that operate reliably in production, not just prototypes
- Work on complex, high-impact engineering workflows with real constraints
- High ownership and influence in a deeply technical environment
Apply if you want to build agent systems that actually work - deterministically, safely, and at scale.
#J-18808-Ljbffr