Operational Excellence – an IT company that develops, implements, and supports IT products for the mining industry, as well as provides production dispatching services based on its own IT products.
We are looking for a technical lead for a product and a team of three engineers. You will be responsible for the architecture, quality, and cost of agents in production, the work plan, and hiring. You will write key components yourself and review the team's code.
Role Responsibilities
- Python platform core: sessions, agent turns, customer policies, accounting; agent cycle per turn budget.
- Migrating users from the pilot architecture to the target architecture without interrupting operations.
- Reducing turn costs: input composition, prefix cache, tool limits, model routing, accounting per user and turn.
- Quality assessment: benchmark from real runs, comparison of Russian models, regression for each prompt, tool, model.
- Company data via MCP with user rights: 1C, KHD, SED, HR, document search with ACL.
- Reliable background procedures and writing to external systems: schedules, human confirmation, exactly one write.
- Sandbox for agent code: per session, without secrets or outgoing connections.
- Team: decomposition, review, working with AI agents for code, hiring. Approving requirements and information security with the customer.
You are a good fit if you have
- Backend experience of 7+ years, with 2+ years as a tech lead/lead engineer, responsible for production.
- Python in production: asyncio, FastAPI, Pydantic, typing, tests. Go - to read and edit.
- LLM agents in production with real users: tool calling, agent cycle, limitations, error handling.
- Understanding of context and cost: call input, prefix cache, history compression, tool limits, turn cost calculation by usage.
- Eval: benchmark datasets, LLM judge and its verification, regression, tracing (Langfuse, OpenTelemetry).
- Hybrid search, reranking, chunking, document access rights.
- MCP, OAuth 2.0/OIDC, token exchange – agent on behalf of the user.
- Durable execution (Temporal, Restate, or similar), idempotency, retries.
- PostgreSQL, Redis, S3, Docker, Kubernetes, GitLab CI.
- Open models via OpenAI-compatible APIs, LiteLLM, or similar.
- Higher technical education.
It's good here because we have
- The opportunity to work from anywhere in the world.
- IT accreditation.
- Corporate benefits program BestBenefit.
- Voluntary medical insurance with dental coverage.
- Access to English language learning.
- Opportunities to take courses and training for professional development in your field.
- Participation in interesting and complex projects in the field of artificial intelligence.
In your cover letter: a few words about your team management experience, education, and what AI you use in development.
