Senior Software Engineer | AI Agents & Cloud Platform (Cast Pilot team)

castaigroupinc; United States; Remote; USD 80,000 - 111,000; Full time

Benefits offered by this job

Equity options

Learning budget

Equipment budget

Personal development days

Extra days off

Team events

Job summary

castaigroupinc is seeking engineers to build and operate AI assistants that answer questions about live Kubernetes and cloud infrastructure, plus the platform for clients to connect their own AI tools securely. You will work across agent behavior, cloud connectivity, permissions, and quality systems, delivering features in short cycles.

Responsibilities cover implementing agent flows, public MCP server tooling with identity controls and safety checks, cloud connectivity to AWS/GCP/Azure, and

Qualifications

• Strong software-engineering fundamentals and the ability to design maintainable systems.
• Production Go experience is preferred; equivalent systems-programming experience in another language is relevant.
• Experience building or operating large-scale, multi-tenant SaaS systems and understanding their production failure modes.
• Solid Kubernetes knowledge, including autoscaling, scheduling, and networking.
• Experience taking a complex project from start to finish, using observability tools, and working with CI/CD and DevOps practices.
• Hands-on use of AI coding agents, strong written and spoken English, and comfort working in an adaptable environment.

Responsibilities

• Develop agent flows, context retrieval, and data connections that ground answers in current infrastructure state.
• Build a public MCP server with carefully scoped tools, identity controls, auditability, and safety checks.
• Maintain connectivity to AWS, GCP, and Azure and develop data foundations for the agents.
• Write production services that interact with cloud APIs, Kubernetes control planes, and language-model APIs.
• Own features from design through rollout; investigate incorrect answers, permission edge cases, and stale data.
• Create evaluations, telemetry, and feedback loops to detect quality regressions; contribute to product direction and participate in on-call rotation.

Skills

Software engineering fundamentals

Go

CI/CD & DevOps

Kubernetes

Observability

English communication

Tools

Cloud provider APIs (AWS/GCP/Azure)

CI/CD tooling

OAuth/OIDC & multi-tenant auth

Job description

Role overview

Build and operate AI assistants that answer questions about live Kubernetes and cloud infrastructure, along with the platform that lets customers connect their own AI clients safely. The work spans agent behavior, cloud connectivity, permissions, and quality systems, with features moving from design to production in short cycles.

Responsibilities

• Develop agent flows, context retrieval, and data connections that ground answers in current infrastructure state.
• Build a public MCP server with carefully scoped tools, identity controls, auditability, and safety checks.
• Maintain connectivity to AWS, GCP, and Azure and develop data foundations for the agents.
• Write production services that interact with cloud APIs, Kubernetes control planes, and language-model APIs.
• Own features from design through rollout; investigate incorrect answers, permission edge cases, and stale data.
• Create evaluations, telemetry, and feedback loops to detect quality regressions; contribute to product direction and participate in on-call rotation.

Requirements

• Strong software-engineering fundamentals and the ability to design maintainable systems and explain architectural choices.
• Production Go experience is preferred; equivalent systems-programming experience in another language is relevant.
• Experience building or operating large-scale, multi-tenant SaaS systems and understanding their production failure modes.
• Solid Kubernetes knowledge, including autoscaling, scheduling, and networking.
• Experience taking a complex project from start to finish, using observability tools, and working with CI/CD and DevOps practices.
• Hands-on use of AI coding agents, strong written and spoken English, and comfort working in an adaptable environment.

Nice to have

• Shipped agentic systems such as MCP services, tool orchestration, RAG pipelines, or evaluation frameworks.
• Practical cloud expertise, including IAM and provider APIs; OAuth/OIDC and multi-tenant authorization experience.
• LLM application evaluation, prompt engineering, latency or cost optimization, or deep managed-Kubernetes knowledge.

Benefits and work setup

Remote-first role for applicants residing in Bulgaria, Croatia, Estonia, Greece, Hungary, Latvia, Lithuania, Poland, Romania, Slovakia, Cyprus, Malta, Finland, Sweden, Ireland, Moldova, North Macedonia, Montenegro, Slovenia, or Ukraine. Gross salary is €6,500–€9,000 depending on experience. Benefits include equity options, a learning budget, equipment budget, extra time for personal development, additional days off, and team events.