Staff AI/LLM Engineer: End-to-End Retrieval & Tooling

We Love AI Jobs; San Carlos, Northern (CA, KY); Hybride; USD 224 000 - 260 000; Plein temps

Résumé du poste

Beacon AI in San Carlos hybrid environment is seeking a Staff Software Engineer to own LLM feature development for aviation safety applications. You will design retrieval and tool-calling flows, build robust APIs, and ensure low latency and scalable costs. You’ll lead safety guardrails and production monitoring across services and teams.

The role emphasizes building end-to-end LLM capabilities with strong emphasis on reliability, observability, and governance in a safety-critical domain.

Qualifications

• Proven track record building production-grade LLM features.
• Experience with retrieval Augmented Generation (RAG) and tool-calling.
• Familiarity with latency, cost, and reliability in safety-critical domains.

Responsabilités

• Build user-facing LLM features, including retrieval, tool-calling, validation, and fallback flows.
• Develop service APIs and workers, and tune caching, latency, and request costs.
• Create evaluations, production metrics, safety guardrails, and observability for deployed systems.

Connaissances

Python

TypeScript

LangChain

RAG and vector search

Outils

AWS Bedrock

OpenAI

Anthropic

OpenSearch

pgvector

Pinecone

Description du poste

Beacon AI in San Carlos hybrid environment is seeking a Staff Software Engineer to own LLM feature development for aviation safety applications. You will design retrieval and tool-calling flows, build robust APIs, and ensure low latency and scalable costs. You’ll lead safety guardrails and production monitoring across services and teams.

The role emphasizes building end-to-end LLM capabilities with strong emphasis on reliability, observability, and governance in a safety-critical domain.