What you'll be doing:

• Launching and maintaining Hive Trace infrastructure, ensuring uninterrupted service operation.
• Automating application build, deployment, and update processes.
• Configuring and supporting telemetry and monitoring systems.
• Monitoring resource usage in Kubernetes, optimizing load.
• Ensuring the security and reliability of services.
• Launching and optimizing LLM model inference, monitoring their performance and stability.
• Promptly responding to production incidents and resolving emerging failures.
• Collaborating with the development team and ML engineers to build a secure product.

What we expect from you:

• Experience with Docker (building and deploying container images).
• Experience with Kubernetes (deploying and updating applications; evaluating and monitoring cluster resource consumption).
• Skills with Helm (chart development).
• Experience with CI/CD (GitLab CI is used on the project).
• Solid Linux knowledge and scripting skills (Bash, Python).
• Understanding of infrastructure security principles and a desire to implement best practices.
• Ability to work in a team and responsibility for results.

What we offer:

• Work on a product that solves current AI security challenges.
• Full-time employment (40 hours per week).
• Remote work option or flexible office schedule.
• Friendly team, ready to support and listen to your ideas.
• Professional growth: participation in conferences, training, and development.
• Competitive salary.