Staff AI Engineer

Ideally 7+ years of software engineering experience, with 3+ years building ML/AI-powered features in production. Proven experience shipping production AI/GenAI features end-to-end. Strong background as a Staff-level product software engineer (not data science or ML-research-only). Experience iteratively improving GenAI-powered features based on quantitative and qualitative signals. Ability to design, run, and evaluate experiments for AI features. Prior on-call experience supporting production systems. Deep expertise in LLMs, prompt engineering, retrieval-augmented generation, and evaluation methods. Proficiency in backend development using Python, Go, Ruby, TypeScript or a similar language. Strong cross-functional skills and a track record of collaborating closely with PMs and designers. Comfort navigating ambiguity and driving clarity in fast-paced environments.

Own end-to-end implementation of AI-powered product features, from prototypes to production. Mentor other engineers on the team, leveling up the team as a whole. Collaborate across the organization to support shipping these features to production. Handle prompt engineering, model tuning, and evaluation strategies to improve reliability and UX. Collaborate with product and design partners in defining and scoping AI-driven experiences. Teach best practices for working with LLMs, including prompt design and evaluation methodologies. Learn deeply about Honeycomb’s workflows and user problems to build truly helpful AI features. Iterate through fast feedback loops, experimentation, and sharing both wins and failures.