#vacancy #middle+ #LLM #SREengineer #python

Position: LLM/SRE Engineer Grade: Middle+ Location: Russian Federation/Republic of Belarus (Republic of Belarus - if there is a legal entity in the Russian Federation) Company: IT People group Rate: we will consider your offer Format: remote, via individual entrepreneur/Social Security Agreement/Civil Law Contract Engagement period: until the end of the year With a possible transfer to the client's staff after six months

Project: Development and implementation of a local multi-agent platform for business process data analysis based on LLM. The platform is deployed on-premise, integrates with corporate systems, and is designed for scaling to other business processes.

Key Requirements: • Commercial development experience from 5 years, Python 3.10+ (at least 2 years) • Experience with LLM / Generative AI from 1 year; daily application of LLM in engineering activities • Solid experience with LangChain / LangGraph / LlamaIndex, RAG, Prompt Engineering • Experience with local LLMs, deployment and maintenance of AI services • Linux (mandatory), Docker from 1 year, server application deployment from 1 year • Ability to design agent scenarios and prototype client applications using LLM Requirements: • Python 3.10+, asyncio, FastAPI, pandas, REST API • LangChain / LangGraph / LlamaIndex, RAG, Prompt Engineering • Vector databases: Qdrant, pgvector, Milvus, and similar • Working with local LLMs: deployment, model management, inference optimization • Linux (proficient), Docker / Docker Compose (proficient), Kubernetes (basic) • Git, GitLab CI / GitHub Actions • Monitoring: Prometheus, Grafana, Loki / ELK (basic level) • PostgreSQL, SQL, Redis • Understanding of information system design principles Additional Requirements: • Experience with Yandex AI Studio / Yandex Cloud • Experience in operating AI infrastructure, SRE / DevOps • Experience with MCP or similar tool integration mechanisms • Experience with GPU infrastructure

Main Tasks: • Development and configuration of a multi-agent system, agent scenarios, and RAG pipelines • Deployment and maintenance of local LLMs, ensuring AI infrastructure operability • Configuration of monitoring, logging, and deployment automation • Participation in incident diagnostics and resolution • Participation in platform development and scaling

Resumes and requirement checks can be sent to 👉 @HR_JuliaG