Published Date
3 weeks ago
Work Arrangement
Hybrid • San Francisco, CA
Open Positions
3 openings
Experience Level
Senior
About the opportunity
Build autonomous multi-step reasoning agents, persistent memory loops, and external tool execution frameworks.
What you will do
- check_circle Architect recursive planning, reflection, and self-correction loops for multi-step autonomous workflows.
- check_circle Build secure, low-latency tool-use execution sandboxes supporting browser automation and terminal environments.
- check_circle Develop hierarchical memory storage systems utilizing vector search and structured knowledge graphs.
- check_circle Evaluate agent behavior using automated red teaming and benchmark suites (SWE-bench, GAIA).
What we are looking for
- arrow_circle_right 4+ years building production software systems with at least 1+ years building LLM agent workflows.
- arrow_circle_right Deep expertise with LangGraph, CrewAI, AutoGen, Python, and OpenAI Function Calling APIs.
- arrow_circle_right Strong background in prompt engineering, context optimization, and model inference latency reduction.
Skills & Tech Stack
Why candidate applications stand out
Verified Technical Credentials
Applications include direct proof-of-work repositories and instructor verification endorsements.
Fast-Track Hiring Visibility
Direct internal referral channels through enterprise partners bypass automated resume discard filters.