Назад
Company hidden
3 дня назад

Senior Artificial Intelligence/Machine Learning Engineer (AWS)

Формат работы
remote (только Ukraine)/hybrid
Тип работы
fulltime
Грейд
senior
Английский
b2
Страна
Ukraine
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 Artificial Intelligence/Machine Learning Engineer (AWS): Building a production-grade document intelligence platform with an accent on agentic systems, high-performance extraction agents, and human-in-the-loop review. Focus on designing ingestion pipelines for degraded inputs, developing confidence-scoring models, and optimizing LLM orchestration on Amazon Bedrock.

Location: Must be based in Ukraine (Remote or Hybrid)

Company

A custom product engineering company that supports multinational organizations and scaling startups to solve complex business challenges.

What you will do

  • Design and build production-grade extraction agents to map unstructured document language to structured schemas.
  • Engineer robust document ingestion pipelines capable of handling low-quality scans and inconsistent layouts.
  • Develop per-field confidence models to drive routing between automated processing and human review.
  • Build RAG knowledge bases to provide domain-specific context and reduce hallucinations.
  • Implement Human-in-the-Loop (HITL) escalation interfaces and feedback loops for model training.
  • Optimize model selection, token usage, and latency strategies within the inference pipeline.

Requirements

  • Must be based in Ukraine.
  • Deep experience with AWS architecture and hands-on work with Amazon Bedrock.
  • Strong background in OCR (Textract or similar) and layout-aware extraction.
  • Proven track record of building multi-step reasoning chains and autonomous agents.
  • Experience with production RAG or LLM pipelines including chunking, retrieval, and grounding.
  • Ability to design HITL systems where corrections serve as training signals.

Nice to have

  • Experience with selective-prediction techniques for confidence calibration.
  • Proficiency in building programmatic evaluation harnesses using golden datasets.
  • Experience working with proprietary domain corpora for data governance.

Culture & Benefits

  • Radical flexibility with the choice to work remotely or from an office.
  • Company-paid medical insurance, mental health support, and legal consultations.
  • Access to Udemy, internal meetups, conferences, and paid certifications.
  • Opportunities for internal mobility across diverse technical domains.
  • Collaborative "One Team" culture in a friendly, open-door environment.

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 →