Software Engineer (Applied AI)
Мэтч & Сопровод
Для мэтча с этой вакансией нужен Plus
Описание вакансии
TL;DR
Software Engineer (Applied AI): Designing and delivering agentic workflows and scalable microservices within a distributed system architecture with an accent on Generative AI integration and RAG pipelines. Focus on implementing operational observability for AI reliability, designing cloud-native event-driven architectures, and establishing AI-SDLC practices.
Location: Remote (Ukraine or Armenia)
Company
is a software development company specializing in high-scale engineering and applied AI solutions.
What you will do
- Architect and build agentic workflows and scalable microservices, primarily using Python.
- Lead the integration of Generative AI capabilities, including LLM APIs and RAG pipelines, into production systems.
- Implement operational practices and autonomous monitors to detect intelligence drift and hallucinations.
- Drive engineering quality by implementing AI-SDLC practices and establishing trace-based quality evaluation.
- Evaluate emerging AI tooling and mentor fellow engineers to contribute to the technical roadmap.
Requirements
- 7+ years of backend or full-stack engineering experience.
- 2+ years of experience building production-grade agentic systems in distributed environments.
- Strong proficiency in Python (preferred) or TypeScript, Go, or Rust.
- Hands-on experience with agentic frameworks such as LangChain, LangGraph, or CrewAI.
- Expertise in AWS, Kubernetes, Terraform, and event-driven architectures (SQS/SNS).
- Must be based in Ukraine or Armenia.
Nice to have
- Experience with React, Next.js, or similar frontend technologies.
Culture & Benefits
- 15 working days of annual paid leave.
- Support from a caring HR team and collaboration with talented colleagues.
- Competitive compensation for your efforts.
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 →