We’re a fast-moving team of aviators, engineers, and operators building an AI platform to make flying safer, more efficient, and more capable. Backed by top investors, we’ve secured a dozen Department of Defense contracts and partnered with major airlines to deliver mission-critical systems. We operate without silos or heavy processes. Small, focused teams own what they build, ship quickly, and learn fast, pushing the boundaries of how humans and AI work together in aviation.
You will ship LLM-powered product features end-to-end. That means designing retrieval and tool-calling flows, writing the services that run them, building evals and guardrails, and watching cost, latency, and quality in production. You’ll partner with the ML/infra teammates on embeddings, indexing, and model hosting, and with the product teammates on user experience and outcomes. We move fast, and we care about reliability in a safety-critical domain.
This role is for engineers early in their LLM/production ML career (2-4 years software engineering experience). You'll implement features within existing service patterns, with architecture and eval design guided by senior engineers.
Build user-facing LLM features
Design and implement retrieval-augmented generation and tool-calling flows using frameworks like LangChain or equivalent primitives, where simpler is better.
Deliver robust JSON and schema-bound outputs with validation, retries, and fallbacks.
Add function calling to integrate with internal tools, search, routing, and data services.
Own the service layer
Ship APIs and workers in Python or TypeScript with clear contracts, streaming, and backoff.
Add caching, request shaping, prompt templates, and context packing to control latency and cost.
Integrate with AWS Bedrock, OpenAI, Anthropic, or self-hosted endpoints as needed.
Retrieval and data prep
Collaborate with infrastructure teammates to develop chunking, embeddings, and indexing capabilities for documents, time series, and multimedia.
Choose and tune vector backends such as OpenSearch, pgvector, or Pinecone.
Keep knowledge bases fresh with data syncs from S3, Aurora, DynamoDB, and external sources.
Evaluation and quality
Create offline evals and golden sets for prompts, retrievers, and tools.
Stand up online metrics for task success, hallucination rate, retrieval precision/recall, p95 latency, and cost per request.
Run A/B tests and prompt/version rollouts with guardrails and canaries.
Safety, privacy, and compliance
Implement content and policy checks, PII detection and redaction, access controls, and auditing.
Design human-in-the-loop paths for sensitive actions.
Handle aviation data with care and follow internal security standards.
Operate what you build
Add tracing, logs, and dashboards for model calls, token usage, errors, and saturation.
Debug tricky failures across retrieval, prompts, tools, and providers.
Shipped LLM apps: You’ve put LLM features in front of users and improved them with data.
Strong builder: Comfortable writing production code, tests, and docs. You keep things simple and observable.
RAG and tools depth: You understand embeddings, chunking, vector search tradeoffs, and function calling.
Quality mindset: You design evals, define success metrics, and iterate based on evidence.
Cost and latency aware: You track p95, hit SLAs, and reduce cost without hurting quality.
Clear communicator: You explain tradeoffs and align partners across product, infra, and security.
Growth mindset: You take direction well, ask good questions, and level up fast with feedback.
Experience with Bedrock, OpenSearch Serverless, pgvector, Pinecone, or Weaviate.
Prompt versioning, guardrails, and provider routing in production.
Multimodal work with time series or video.
Familiarity with GPU inference, Triton, or TensorRT-LLM.
Aviation or other safety-critical domain exposure.
DevOps basics for CI/CD, IaC, and secure secrets handling.
Transform an internal knowledge base into a low-latency RAG service, complete with explicit schemas and evaluations.
Add tool-calling to automate a repetitive cockpit or ops workflow with guardrails and audit trails.
Reduce the cost per request through improved chunking, caching, and prompt refactoring, while maintaining task success rates.
Work Location
This is a hybrid role based in San Carlos, CA, with 3+ days per week onsite and the option to work remotely on remaining days.
Perks & Benefits (Full-Time Employees)
Healthcare: 100%* of employee medical premiums covered; 25% for dependents
Time Off: 3 weeks PTO plus 13+ paid company holidays
401(k): Offered (no current employer match, but we are committed to enhancing this benefit in the future)
Due to U.S. export control regulations, we can only hire U.S. Persons (U.S. citizens, Green Card holders, lawful permanent residents, or individuals granted asylum or refugee status). We are unable to provide visa sponsorship or support visa transfers. All work must be performed in the United States.
Beacon AI is an equal opportunity employer and does not discriminate based on race, color, religion, sex, sexual orientation, gender identity or expression, national origin, age, genetic information, disability, veteran status, or any other protected characteristic. We prohibit harassment or discrimination of any kind in the workplace and comply with all applicable federal, state, and local employment laws.
Want to know if this job is worth applying to?
San Carlos - Hybrid
Hybrid
Not Available
