Senior AI/LLM Engineer - End-to-End ML Systems

AI Chopping Block, Inc.; San Carlos, Northern (CA, KY); Hybrid; USD 180,000 - 230,000; Full time

Benefits offered by this job

Healthcare coverage

PTO 3 weeks

401(k)

Job summary

Beacon AI in San Carlos, CA is hiring senior ML engineers to own end-to-end features in safety-critical aviation AI. You will design retrieval and tool-calling flows, implement robust APIs and guardrails, and balance latency with cost while shipping production ML services.

You will collaborate across product, infra, and security, tackle data prep and evaluation tasks, and ensure privacy, safety, and compliance. Hybrid work option with on-site in San Carlos and remote days.

Qualifications

• 5-8 years experience in production ML/LLM systems.

Responsibilities

• Build user-facing LLM features with retrieval-augmented generation and tool-calling flows.
• Own the service layer with APIs and workers in Python or TypeScript.
• Handle retrieval, data prep, embeddings, and indexing capabilities.
• Develop evaluation metrics and guardrails for quality, cost, and latency.
• Ensure safety, privacy, and compliance with auditing and access controls.
• Operate and monitor what you build with tracing and dashboards.

Job description

Beacon AI in San Carlos, CA is hiring senior ML engineers to own end-to-end features in safety-critical aviation AI. You will design retrieval and tool-calling flows, implement robust APIs and guardrails, and balance latency with cost while shipping production ML services.

You will collaborate across product, infra, and security, tackle data prep and evaluation tasks, and ensure privacy, safety, and compliance. Hybrid work option with on-site in San Carlos and remote days.