Design and build AI-powered user features: Implement prompt-based and retrieval-augmented systems (RAG) that answer complex sports questions and generate insights.
Build agents and workflows that combine deterministic logic with LLM reasoning.
Prototype and iterate fast: Use prompting, tool orchestration, and retrieval design to rapidly build and refine AI behaviors.
Collaborate with Eval Engineers to build golden sets and automate quality checks before release.
Work closely with the LLMOps Platform team: Use shared eval frameworks, prompt registries, and model gateways.
Provide feedback loops to improve platform reliability, latency, and safety.
Integrate with deep learning and data systems: Combine structured stats, tracking data, and video-derived features into AI-powered applications.
Build APIs and UI layers that expose insights to coaches, teams, and partners.
Push the limits of applied AI: Explore how LLMs, retrieval, and deterministic logic can create novel sports analytics tools.
Use AI internally to accelerate development (code generation, testing, debugging).

5+ years of experience as a Software Engineer, ML Engineer, or AI Developer
Proficiency in Python and TypeScript/JavaScript (Node.js or React)
Hands-on experience with LLM frameworks (LangChain, LlamaIndex, Semantic Kernel, Haystack)
Strong understanding of prompt engineering, retrieval-augmented generation, and evaluation workflows
Ability to design robust backend systems integrating APIs, vector databases, and orchestration layers
Curiosity and creativity to turn ambiguous problems into structured, production-quality systems.

AI Application Engineer

Key skills