Lead design and implementation of AI-powered features: LLM integrations, retrieval-augmented generation, agentic pipelines, and AI-augmented workflows.
Own prompt engineering rigor: structured prompts, evaluation, iteration based on production signal, and documentation of effective approaches.
Develop LLM integration patterns for the pod: streaming responses, function calling, context window management, fallback handling, and evaluation.
Recommend AI solution approaches (prompting, RAG, fine-tuning, agentic patterns) based on constraints; decide when to apply which approach.
Contribute production-grade code in Ruby/Rails and TypeScript/React; maintain high quality for both AI and non-AI features.
Collaborate with the customer-facing agent platform to build, iterate, and deploy AI capabilities.
Work within a 3-week Agile cadence; own on-call shifts and production operations (latency, cost at scale, multi-tenant routing, data boundaries); ship features iteratively.
Conduct deep code reviews, share LLM integration knowledge across pods, mentor teammates, and promote shared ownership of AI systems.