Назад
Company hidden
3 дня назад

Senior LLM Engineer (AI)

173 000 - 225 000$
Формат работы
hybrid
Тип работы
fulltime
Грейд
senior
Английский
b2
Страна
US
Вакансия из списка Hirify.GlobalВакансия из Hirify Global, списка международных tech-компаний
Для мэтча и отклика нужен Plus

Мэтч & Сопровод

Для мэтча с этой вакансией нужен Plus

Описание вакансии

Текст:
/
TL;DR
Senior LLM Engineer (AI): Building user-facing LLM features and production services for an aviation AI platform with an accent on retrieval-augmented generation, tool calling, evaluation, and safety. Focus on designing reliable RAG workflows, controlling latency and cost, measuring model quality, and operating AI systems in a safety-critical domain.

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

Salary: $173,000–$225,000 base salary annually, plus equity.

Company

hirify.global builds AI systems and an AI platform that make flying safer, more efficient, and more capable, supporting aviation customers and Department of Defense contracts.

What you will do

  • Design and ship user-facing LLM features using retrieval-augmented generation, tool calling, structured outputs, validation, retries, and fallbacks.
  • Build and operate Python or TypeScript APIs and workers with streaming, caching, prompt templates, context packing, and backoff.
  • Develop retrieval and data-preparation capabilities using chunking, embeddings, vector search, indexing, and data synchronization.
  • Create offline and online evaluations covering task success, hallucination rate, retrieval quality, latency, and cost.
  • Implement guardrails, PII detection and redaction, access controls, auditing, and human-in-the-loop workflows for sensitive actions.
  • Add observability and debug failures across retrieval, prompts, tools, model providers, and production infrastructure.

Requirements

  • 5–8 years of engineering experience, including experience with production ML or LLM systems.
  • Shipped LLM applications used by end users and improved them using production data.
  • Strong production coding, testing, documentation, architecture, and service ownership skills.
  • Knowledge of embeddings, chunking, vector search tradeoffs, function calling, evaluations, guardrails, and provider routing.
  • Ability to manage quality, p95 latency, SLAs, and cost while communicating technical tradeoffs across product, infrastructure, and security.
  • Must be a U.S. Person and have authorization 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.
  • Experience with multimodal systems, time series, video, GPU inference, Triton, or TensorRT-LLM.
  • Aviation or other safety-critical domain experience.
  • DevOps experience with CI/CD, infrastructure as code, and secure secrets handling.

Culture & Benefits

  • Small, focused teams own what they build and ship quickly without heavy processes or silos.
  • Healthcare coverage includes 100% of employee medical premiums and 25% for dependents.
  • Three weeks of paid time off and 13 or more paid company holidays.
  • 401(k) plan available; there is currently no employer match.
  • Full-time employment with equity eligibility.

Будьте осторожны: если работодатель просит войти в их систему, используя iCloud/Google, прислать код/пароль, запустить код/ПО, не делайте этого - это мошенники. Обязательно жмите "Пожаловаться" или пишите в поддержку. Подробнее в гайде →