Key responsibilities
-
Build and ship new agent capabilities on the internal platform, deployed company-wide.
-
Contribute to agent-platform architecture (tool/skill surfaces, runtime, deployment patterns).
-
Work on LLM fine-tuning / custom-inference experiments — e.g. cheaper/faster models that hold frontier-level reliability for monitoring and ops workflows.
-
During onboarding, read and improve existing internal apps (real platform improvements, not throwaway exercises).
-
Help run weekly internal AI Office Hours teaching the broader company to use our AI agent tools.
Required qualifications
-
Pursuing a CS / software-engineering (or closely related) degree.
-
Strong programming fundamentals; comfortable in Python.
-
Working familiarity with LLMs / AI APIs and a genuine eagerness to build with them.
-
Comfortable with Git and collaborative development.
Preferred / nice-to-have
-
Experience with agent frameworks, RAG, MCP, or prompt/tool design.
-
Exposure to model fine-tuning or inference optimization.
-
Cloud experience (AWS).
-
Self-directed; thrives with real ownership in a fast-moving environment.