Senior Software Engineer - AI Agents & Cloud Platform

About the role

Cast AI builds AI assistants that answer questions about live Kubernetes clusters and cloud infrastructure, and is opening a public, permission-aware MCP server so customers can plug CAST AI into their own AI clients. The Cast Pilot team is looking for a Senior Software Engineer to build the systems behind the AI assistant, the MCP server and cloud connectivity. The role is remote-first and open to candidates living in the listed European countries.

Key responsibilities

• Design and build the systems behind the AI assistant: agent flows, context retrieval and data connections to live Kubernetes infrastructure.
• Build and evolve the public, permission-aware MCP server, with curated tools, identity, audit and safety gates.
• Develop and maintain cloud connectivity across AWS, GCP and Azure, and write production Go services that interact with cloud provider APIs, the Kubernetes control plane and LLM APIs.
• Own features end-to-end, from design through testing and production rollout (most projects ship in 1 to 4 weeks).
• Debug complex issues such as wrong agent answers, cross-cloud permission edge cases and data freshness problems at scale.
• Build the quality harness: evals, telemetry and feedback loops to prevent regressions.
• Contribute to product direction and the backlog, and take part in the on-call rotation.

Required profile

• Strong software engineering fundamentals and generalist ability, with production experience in Go (strongly preferred).
• Experience building or operating large-scale SaaS platforms and complex projects end-to-end.
• Hands-on experience with AI coding agents and agentic workflows, and production observability tooling.
• CI/CD and DevOps experience, strong English, and a startup mindset.
• Standout: shipped agentic systems (MCP servers, agent gateways, RAG pipelines, etc.), deep hands-on experience with AWS, GCP or Azure, LLM quality experience, OAuth/OIDC knowledge, or Kubernetes/cloud-native OSS contributions.

Required skills

• Go, Kubernetes, Terraform, PostgreSQL, ClickHouse
• Temporal, gRPC, REST, Prometheus, Grafana, Loki, Tempo, PostHog
• GitLab/GitHub CI, ArgoCD, Kargo
• Preferred: AWS, GCP, Azure, EKS/GKE/AKS internals, OAuth 2.0 / OIDC

What we offer

• Salary of EUR 6,500 to 9,000 gross depending on experience, equity options and a flexible remote-first environment.
• 10% of work time for personal projects, learning budget, annual hackathon, extra days off and equipment budget.

Hiring process: recruiter screening, hiring manager interview, technical system design interview, live coding, culture check, and possibly a background check. No visa sponsorship is provided.