Beacon AI
US - California - San Carlos
View Company Profile /
<< Go Back
Lead the design and delivery of user-facing LLM features, including retrieval and tool-calling workflows, production services, evaluations, and safety controls. Own reliability and performance in production while collaborating across product, infrastructure, ML, and security teams on retrieval, data preparation, monitoring, and technical direction.
Requirements: Candidates should have at least eight years of experience and a record of setting technical direction or standards across systems or teams. They should have shipped LLM applications, be proficient in production software development, and demonstrate depth in RAG, embeddings, vector search, tool calling, evaluation, observability, and cost and latency optimization.
Key Skills: Large Language Models, Retrieval-Augmented Generation, Python, TypeScript, Vector Search, Function Calling, Prompt Engineering, Model Evaluation, API Development, AWS, Observability, Data Privacy, Technical Leadership, Cost and Latency Optimization
Benefits: Health Insurance, Paid Time Off, Paid Company Holidays, 401(k)
© 2026 engineeringjobs.net, Inc. All Rights Reserved.
Terms of Service | Privacy
Powered by JOBBEX