Build and improve agent runtime: routing, query rewrite, RAG/FAQ.
Extend the Tool Server: add/optimize tools (web search, data APIs).
Strengthen evaluation: create eval datasets; measure routing and answer quality.
Improve observability: traces, metrics, logging (Opik/Pinpoint); dashboards and alerts.
Fix pipeline bugs and write integration tests with mock-LLM replay.

🎯 Requirements

Must-have: Python + clean coding; CI, reviews, typing.
Must-have: LLM basics—prompting, RAG, tool calls.
Must-have: Reasoning about correctness; write tests; async debugging.
Must-have: Available for a sustained internship.
Nice-to-have: Agent frameworks (AgentScope/LangChain/LlamaIndex).
Nice-to-have: Vector search/embeddings and LLM observability.

🎁 Benefits

Ship real features in production AI agent.
Mentorship from senior BE/DS/algo engineers.
Hands-on exposure to full LLM-app stack: RAG, tool servers, evals.
Work-from-home arrangement; flexible schedule.

Apply on employer's website

This employer gathers applications via their own applicant tracking system.

You will be redirected to an external application form.

Share job

Meet JobCopilot: Your Personal AI Job Hunter

Automatically Apply to Engineering Jobs. Just set your preferences and Job Copilot will do the rest — finding, filtering, and applying while you focus on what matters.

Activate JobCopilot