SRE

We currently have several large-scale projects and are expanding our infrastructure team. Our product is an advanced platform for creating and managing AI agents. It can be deployed directly inside a customer’s infrastructure and delivered as an enterprise solution, while also being available as a SaaS version. Under the hood, there is real-time voice and telephony, GPU and LLM inference, streaming analytics, and all of this runs both in the cloud and on-prem, including in banking environments. There is a lot of infrastructure; it is complex, interesting, and sometimes at the edge of what is possible. That is why we are looking for a strong SRE who, like us, cares about making systems transparent, reliable, and built the right way. This is a role for a strong, independent engineer. A Senior SRE with real influence and a voice in how things are built and operated. You will also handle DevOps tasks for the team, but your main focus and area of expertise should be SRE: reliability, observability, incident management, and performance under load. - 5 years in SRE/DevOps. You have not just seen production; you have been responsible for the reliability of high-load production systems. - Deep, practical understanding of Docker and Kubernetes. You have operated them in production, not just used them in tutorials. - Mature understanding of metrics and alerts, with real hands-on experience writing, tuning, and maintaining them. - Practical experience with Prometheus, Alertmanager, and Grafana. - Ability and willingness to build dashboards and make them clear, useful, and easy to work with. - Experience with SLIs/SLOs, reliability management, incident investigation, and postmortems. - Experience with load testing and basic capacity planning. - Python: you can write code and confidently read and modify other people’s code for automation, exporters, tooling, and related tasks. - Cloud experience with GCP and/or AWS, strong Linux skills, and solid networking knowledge at an operational level. - DevOps fundamentals: CI/CD and infrastructure as code, including GitHub Actions, Terraform, Ansible, and similar tools. - Willingness to understand and support the product in customer environments, including on-prem deployments. - Ownership mindset: you take responsibility for a task, drive it to completion, and think one step ahead. - Friendly, non-toxic, and pleasant to work with. - Strong communication with developers: you can clearly and constructively explain your position, defend it when needed, and find common ground. - Willingness and ability to mentor, teach, and share knowledge with others. - Analytical mindset: you dig down to the root cause instead of just treating symptoms. - Proactivity: you would rather prevent an outage than heroically fight it later. - Strong attention to detail and reliability. Nice to have - Experience using AI agents for routine and recurring tasks. - Real-time telephony: SIP, FreeSWITCH, RTP, WebRTC. - GPU/ML serving: Triton, vLLM, RunPod, Nebius, Lambda, run:ai, DCGM; understanding of the specifics of deploying LLM/ML models. - Streaming data and analytics: Kafka, ClickHouse. - Deep experience with IaC and GitOps, such as Terraform, Ansible, ArgoCD; logging with Loki/ELK; gRPC. - Experience working in isolated and highly secure environments. - Experience preparing systems for significant growth in load. - You will be responsible for the reliability of our services: SLIs/SLOs, availability, and identifying and eliminating bottlenecks across the system. - You will set up monitoring for services, metrics, alerts, and dashboards. This will rarely come as a clearly defined task; more often, you will decide what is important to measure and bring it to a clear, usable view. - You will build and maintain Grafana dashboards that people actually use, both our team and our customers. - You will run load testing, analyze the results, and provide recommendations on resources and scaling. - You will investigate incidents, participate in on-call rotations, write and lead postmortems, and ensure the same failure does not happen again. - You will work closely with developers: communicate and defend your position, challenge technical decisions, and find win-win solutions. - You will develop and support Kubernetes-based infrastructure across our clouds, including GCP and AWS, automate routine work, and help with CI/CD and general team tasks. - You will take part in delivering and support