Overview

Join the flagship AI track and ship real LLM-powered features end-to-end. You will design prompts, build agentic workflows, integrate models into a production SaaS product, and stand up evaluation pipelines that keep quality high as the system evolves. You work alongside senior AI engineers and product partners on problems that ship to real users.

Responsibilities

• Design and implement LLM-powered features (RAG, tool use, multi-step agents)
• Build prompt templates, function-calling schemas, and structured output validators
• Stand up evaluation pipelines (eval sets, scoring, regression checks) for model quality
• Integrate AI capabilities into a production backend with proper observability
• Iterate on accuracy, latency, and cost based on real metrics
• Document experiments, prompts, and architectural decisions clearly

Requirements

• Solid Python proficiency
• Foundational understanding of LLMs, embeddings, and prompt engineering
• Comfort calling REST/JSON APIs and handling async workflows
• Familiarity with Git and modern development workflows
• Strong analytical mindset and willingness to measure everything

Nice to Have

• + LangChain / LlamaIndex
• + Vector databases
• + Agent frameworks
• + Evaluation tooling (Ragas, DeepEval)
• + TypeScript / Node.js