AI HUB SberWorks is a strategic platform for the development and operation of AI-agents within AI PDLC and for providing AI functionality in OneWork. We are building a multi-agent environment that ensures the full agent lifecycle – from the first commit to industrial operation.
Our mission is to reduce the time to create the first agent from months to one week and to automate all manual onboarding processes. We are already integrating with key corporate systems (OneWork, SberSpace, MCP, EDMS) and preparing the platform for scaling to mass corporate use in 2026.
We are looking for an engineer who will help us build a reliable, automated, and scalable infrastructure for the industrial operation of AI-agents.
Responsibilities:
- Development of the AI HUB SberWorks platform:
- Participation in the design and operation of a multi-agent execution environment based on SberWorks and modern agent frameworks.
- Ensuring the reliability and fault tolerance of a unified CI/CD pipeline for AI-agents.
- Automating agent onboarding and update processes, bringing teams closer to the goal of 100% automation (Zero-touch operations).
- CI/CD and agent lifecycle automation:
- Development and support of continuous integration and delivery pipelines adapted to the specifics of AI PDLC.
- Implementation of Infrastructure as a Code (IaC) practices for managing the agent execution environment.
- Automation of agent artifact registration and versioning.
- Integration and monitoring:
- Ensuring seamless integration of AI HUB with adjacent systems: OneWork IDP, SberSpace, MCP.
- Configuring monitoring of agent and infrastructure performance, integration of key metrics (Time to First Agent, Lead Time) into the IDP dashboard.
- Preparing the infrastructure for scaling: from supporting pilot teams to 90% coverage of all new AI-agents by 2026.
- Interaction with agent development teams:
- Assisting teams in onboarding their agent solutions to the platform, consulting on best practices.
- Participation in migrating existing internal agent solutions from pilot teams to the unified AI HUB environment.
- Collecting feedback from early users to improve the CI/CD pipeline and infrastructure.
We expect you to:
- Have commercial DevOps experience of 3+ years.
- Be proficient in Docker and container orchestration systems (Kubernetes).
- Have experience with configuration management systems (Ansible, ArgoCD) and IaC tools (Terraform).
- Understand the principles of building CI/CD pipelines (GitLab CI / Jenkins).
- Be able to work with monitoring and logging systems (Prometheus/VictoriaMetrics, Grafana, Loki/ELK).
- Be familiar with Linux administration basics and network interactions in a microservice architecture.
- Be ready to learn new technologies (multi-agent frameworks, RAG, MCP) and propose improvements.
Will be a plus:
- Understanding of the specifics of AI-agent or ML-model lifecycles.
- Practical experience in developing and deploying autonomous AI-agents using a base environment (MCP, RAG).
- Experience with agent orchestration platforms or serverless environments.
- Experience integrating corporate systems (OneWork, SberSpace).
- Interest in artificial intelligence and agent systems.
Conditions:
- Stable salary and social support for employees.
- Extended voluntary medical insurance from the first day of employment for employees and preferential medical insurance for relatives.
- Free SberPrime+ subscription, discounts on products from partner companies.
- Corporate pension program.
- Corporate training at the company's expense.
- Employee referral program: you can invite acquaintances and professionals to the team and receive a reward of up to 100 thousand rubles.
- Official employment from the first day.
- Corporate gym and discounts at partner gyms.
- Powerful hardware, additional monitors, and everything needed for productive work.
- Modern office with a "smart home" system, recreation areas, and balance boards.
- Agile work with the best in the IT industry: 2000 product teams and opportunities for internal mobility.
