Backend / ML Infrastructure / MLOps Engineer
Published: 12 June 2026
Updated: 2 weeks ago
📝 Description
#vacancy
Work format: remote (no office)
City: any, working across the Russian Federation; comfortable overlapping with Moscow time (MSK ±3 h)
Employment: project-based, with the potential to transition to a permanent role
Salary range: from 180,000 to 250,000 ₽/month (net)
Job description:
We are looking for a Backend / ML Infrastructure / MLOps Engineer for a project — an AI assistant for Russian case law (SaaS for lawyers).
We are building a product with a clear architecture: we assemble a RAG from an array of Russian court documents and connect a self-hosted LLM with tools to it. The user formulates a request in natural language and receives a detailed answer with links to specific cases. The prototype is already working, parsing and indexing are underway — the task is to finalize the product assembly.
Stack: Python and TypeScript, Postgres, Qdrant (vector search), embeddings, RAG + Reranking (Qwen), self-hosted LLM inference on private GPUs, S3 (Backblaze B2), Sentry.
What's already completed:
— Semantic search of case law, selection of similar cases, analysis of court positions, summaries of specific cases.
Partially completed: analytics by instances and judges; links to specific cases.
Upcoming tasks (scope of work):
— Statistical tools for actor profiling
— Refine the infrastructure
— Generation of procedural documents (claims, appeals, complaints) with export to .docx/.pdf
— Assembly of RAG + reranking in production and stable self-hosted LLM inference
— API, monitoring, and quality logs of responses, load stability
Who we are looking for: middle / junior-to-middle, proficient in Python (TypeScript is a plus). Main requirement is the ability to understand existing code and bring features to production. Experience with RAG / LLM / vector search / parsing large text datasets is a big plus. There is a detailed backlog and a lead developer who will conduct interviews and onboard you.
Company name: Rusyaev Educational Products LLC
Contacts: Andrey, @metaskazki
#ML #RAG #LLM #Python #MLOps #backend #remote