Senior LLM Engineer — End-to-End AI in Aviation

Beacon AI; San Carlos (CA); Hybrid; USD 170,000 - 210,000; Full time

Benefits offered by this job

Healthcare premiums covered

3 weeks PTO + holidays

401(k) with future enhancements

Job summary

Beacon AI in San Carlos, CA is hiring senior engineers to own end-to-end LLM features, including design, implementation, and production delivery. You'll collaborate across ML/infra and product teams to build retrieval and tool-calling flows, while ensuring reliability, cost efficiency, and safety in a safety-critical aviation domain.

The role requires 5-8 years of experience in production ML/LLM systems, strong coding skills in Python/TypeScript, and comfort with cloud and vector backends.

Qualifications

• Senior engineers with 5-8 years in production ML/LLM systems.
• Ability to own a feature end-to-end from design to production.
• Strong knowledge of retrieval, tool-calling, and scalable APIs.

Responsibilities

• Design and implement retrieval-augmented generation and tool-calling flows using LangChain or equivalent.
• Deliver robust JSON outputs with validation, retries, and fallbacks.
• Add function calling to internal tools, search, routing, and data services.
• Ship APIs/workers in Python or TypeScript with clear contracts and backoff.
• Add caching, prompt templates, and context packing to reduce latency and cost.
• Integrate with Bedrock, OpenAI, Anthropic, or self-hosted endpoints.
• Develop chunking, embeddings, indexing with infrastructure teams.
• Tune vector backends like OpenSearch, pgvector, Pinecone.
• Keep KBs fresh with data syncs from S3, Aurora, DynamoDB, etc.
• Create offline evals and online metrics for prompts and retrievers.
• Run A/B tests with guardrails and canaries.
• Implement content/policy checks and PII redaction.
• Design human-in-the-loop paths for sensitive actions.
• Add tracing, logs, dashboards for model calls and costs.

Skills

LLM development

Production code

Observability

Cost awareness

Tools

LangChain

AWS Bedrock

OpenAI API

Anthropic

Weaviate/OpenSearch

Job description

Beacon AI in San Carlos, CA is hiring senior engineers to own end-to-end LLM features, including design, implementation, and production delivery. You'll collaborate across ML/infra and product teams to build retrieval and tool-calling flows, while ensuring reliability, cost efficiency, and safety in a safety-critical aviation domain.

The role requires 5-8 years of experience in production ML/LLM systems, strong coding skills in Python/TypeScript, and comfort with cloud and vector backends.