AI Engineer (LLM)

Location: Hybrid in San Carlos, California, with 3+ days per week onsite and remote work allowed on remaining days. All work must be performed in the United States.

Salary: $224,000–$260,000 annual base salary, plus equity.

Company

hirify.global builds AI systems and an AI platform for safer, more efficient aviation, serving airlines and Department of Defense programs.

What you will do

• Build and ship user-facing LLM features using retrieval-augmented generation, tool calling, structured outputs, validation, retries, and fallbacks.
• Develop Python or TypeScript APIs and workers with streaming, backoff, caching, prompt templates, and context-packing strategies.
• Partner with infrastructure engineers on chunking, embeddings, indexing, vector backends, and knowledge-base synchronization.
• Create offline and online evaluations for prompts, retrievers, and tools, including quality, latency, cost, and hallucination metrics.
• Implement safety and privacy controls such as policy checks, PII redaction, access controls, auditing, and human-in-the-loop workflows.
• Operate production systems with tracing, logs, dashboards, canary rollouts, and debugging across models, retrieval, tools, and providers.

Requirements

• 8+ years of engineering experience with a track record of owning systems or defining technical standards used by other teams.
• Experience shipping LLM features to users and writing production code, tests, and documentation.
• Strong knowledge of RAG, embeddings, chunking, vector search, function calling, and structured model outputs.
• Experience designing evaluations, success metrics, guardrails, prompt iteration, and production quality improvements.
• Ability to lead ambiguous, cross-team technical problems and communicate tradeoffs across product, infrastructure, and security.
• Must be a U.S. Person and already authorized to work in the United States; visa sponsorship and visa transfers are not available.

Nice to have

• Experience with Bedrock, OpenSearch Serverless, pgvector, Pinecone, or Weaviate.
• Production experience with prompt versioning, guardrails, provider routing, multimodal data, time series, or video.
• Familiarity with GPU inference, Triton, TensorRT-LLM, CI/CD, infrastructure as code, and secure secrets management.
• Aviation or other safety-critical domain experience.

Culture & Benefits

• Small, focused teams with end-to-end ownership and fast delivery.
• Healthcare coverage includes 100% of employee medical premiums and 25% of dependent premiums.
• Three weeks of paid time off plus 13 or more paid company holidays.
• 401(k) plan available; there is currently no employer match.
• Mission-critical work focused on aviation safety and human-AI collaboration.