Senior Software Engineer – AI Agents, Cloud Platform

This is a fully remote position, open to applicants in Estonia.

📋 Description

• Design and develop systems that power the AI assistant, encompassing agent flows, context retrieval, and real-time Kubernetes infrastructure data connections.

• Create and enhance a public, permission-aware MCP server equipped with curated tools, identity management, auditing, and safety mechanisms.

• Establish and sustain cloud connectivity across AWS, GCP, and Azure, along with the foundational data structures.

• Produce production-grade Go services that interact with cloud provider APIs, the Kubernetes control plane, and LLM APIs in real-time.

• Take ownership of features from initial design through implementation, testing, and production launch.

• Troubleshoot unique issues, including incorrect agent responses, cross-cloud permission challenges, and large-scale data freshness concerns.

• Develop quality assurance harnesses featuring evaluations, telemetry, and feedback loops to enable agent enhancements without regressions.

• Contribute to shaping product direction and managing the backlog.

• Engage in the team's on-call rotation.

⛳️ Requirements

• Strong foundation in software engineering principles, emphasizing clean abstractions, maintainable code, and architectural rationale.

• Generalist with comfort in debugging distributed systems, designing authentication flows, and optimizing agent behavior.

• Production experience in Go is highly preferred; comparable systems programming expertise will also be considered.

• Experience in developing or managing large-scale SaaS platforms in a production environment, particularly multi-tenant systems and high-traffic settings.

• Comprehensive understanding of Kubernetes, encompassing autoscaling, scheduling, and networking.

• Demonstrated ability to drive a complex project from start to finish.

• Hands-on experience with AI coding agents and agentic development methodologies.

• Production experience with observability tools.

• Familiarity with CI/CD and DevOps practices.

• Strong verbal and written communication skills in English.

• Adaptable, proactive, and comfortable navigating ambiguity.

• Experience in building deployed agentic systems, such as MCP servers or clients, agent gateways, tool-use orchestration, RAG pipelines, or evaluation frameworks.

• Extensive hands-on experience with AWS, GCP, or Azure, including IAM, compute, networking, and APIs.

• Experience with LLM application quality, evaluations, prompt engineering at scale, as well as agent-loop latency and cost optimization.

• Knowledge of OAuth 2.0/OIDC and multi-tenant authorization design.

• In-depth knowledge of EKS, GKE, or AKS internals.

• Contributions to Kubernetes or cloud-native open-source software.

• A background check may be conducted during the final recruitment stage.

• Candidates must reside in an eligible European country as Cast AI does not provide visa sponsorship or work permits.

🏝️ Benefits

• Equity options.

• Flexible, remote-first global work environment.

• 10% of work time allocated for personal projects or self-improvement.

• Learning budget for professional and personal development, including international conferences and courses.

• Annual hackathon.

• Team-building budget and company events.

• Equipment budget.

• Additional days off.

• Opportunity to work on genuinely novel problems and production AI platforms.

• Engage with real users and experience fast product delivery.