Назад
Company hidden
4 дня назад

ML Engineer, Retrieval & Grounded Generation (AI)

165 000 - 200 000$
Формат работы
remote (только USA)
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
ML Engineer, Retrieval & Grounded Generation (AI): Building a production retrieval and grounded-generation platform that connects external evidence feeds, retrieves provenance-tracked records, and produces cited explanations with an accent on embeddings, vector retrieval, model serving, and citation reliability. Focus on testing grounding failures, designing rollback and telemetry infrastructure, and maintaining secure inference paths for restricted environments.

Location: Remote, USA; occasional travel to hirify.global headquarters, customer sites, and vendor facilities may be required.

Salary: $165,000–$200,000 per year.

Company

hirify.global develops AI, mathematical optimization, data analytics, and software engineering solutions for resilient optimization of complex systems, including secure government applications.

What you will do

  • Build embeddings, vector storage, and retrieval across large provenance-tracked evidence bases.
  • Integrate language models so generated explanations remain bound to cited source records and test citation failures.
  • Design prompts and output schemas for model-assisted processing.
  • Own model packaging, versioning, serving, rollback, and telemetry for retrieval and generation quality.
  • Provide bounded model assistance for narrative extraction, with outputs tied to source passages and recorded rule context.
  • Maintain a modular self-hosted or managed serving path alongside the primary inference service.

Requirements

  • 5+ years of experience, including building a production or near-production retrieval-augmented generation system.
  • Strong Python skills and hands-on experience with embeddings and vector retrieval at scale.
  • Detailed understanding of retrieval design, vector stores, grounding tests, citation failures, and rollback.
  • US citizenship is required.
  • Active US Secret clearance is required to start.

Nice to have

  • Experience deploying models in restricted or air-gapped environments.
  • Self-hosted or open-weight model operation.
  • Fine-tuning, adapters, or custom embeddings.
  • Federal DevSecOps, RMF, ATO, or Department of War cloud environment experience.
  • Active Top Secret clearance.

Culture & Benefits

  • Fully remote, results-based work environment.
  • Competitive salary, bonus, and equity package.
  • Employer-paid medical, dental, and vision insurance for employees and families.
  • Unlimited PTO with manager approval and a flexible workday.
  • Fourteen weeks of fully paid parental leave.

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 →