We are the «Triple A» team of the «Corporate Collection» tribe at Sberbank. We create advanced solutions for working with corporate clients facing problem debt. Our product is a suite of modern services, intelligent models, and tools that allow for effective management of collection processes.
We develop/support AI agents, ML models, and their infrastructure to automate customer interaction processes and support decision-making by bank employees.
The team's focus is on creating production-ready AI systems, where AI agents integrate with internal bank services, work with documents and data, and are used in real business processes.
Responsibilities
What you will be doing:
- Implementing and supporting AI/ML models and AI agents in industrial operation (assembly, deployment)
- Developing infrastructure for AI agents and ML services: integration with internal APIs and services (REST, Kafka), working with data and documents (including OCR), organizing data storage, implementing RAG approaches
- Automating CI/CD pipelines for models and AI services
- Ensuring the reliability and observability of AI systems: monitoring, logging, tracing, quality control (model drift, business metrics), error handling (retry, fallback)
- Operating and integrating ML models in production: supporting batch processes (including on PySpark), using models as part of AI agents and services.
Requirements
- 2+ years of experience in MLOps, DevOps, or backend development with a focus on ML/ AI systems
- Experience with industrial ML/ AI systems: monitoring, observability (Prometheus, Grafana, OpenTelemetry)
- Skills in working with Kubernetes (Istio Service Mesh - a plus)
- Experience building CI/CD pipelines (Jenkins, ArgoCD)
- Understanding of AI/LLM system principles: orchestration, tool execution, production limitations
- Experience with frameworks for writing LLM/AI agents (LangChain, LangGraph, Openclaw, etc.)
- Desire to develop in the field of AI agents and adapt infrastructure for new tools.
Conditions
- Work format: office in Moscow, hybrid - by agreement, Business Center, Kutuzovsky Prospekt, d. 32, bldg. 1
- Annual salary review and annual bonus
- More than 400 educational programs from SberUniversity for professional and career development
- Extended voluntary medical insurance (DMS), preferential insurance for family members
- Free SberPrime+ subscription, discounts on products from partner companies
- Reward for recommending friends to the Sber team.
