Senior AI Platform Infrastructure Engineer

About the role

A top-tier hedge fund is expanding its AI agent platform, which currently runs 1,500+ agents in production. The partner is hiring Senior Platform Engineers to build across the whole stack, from the infrastructure to the agents and MCP tools that run on it. The team owns both the agents, MCP servers and tools, and the Kubernetes/AWS platform with event-driven systems underneath.

Key responsibilities

• Build secure communication between agents, agents that manage other agents, and shared memory with proper access controls
• Build evals that keep the system reliable at scale
• Own the agents, MCP servers and tools, and the Kubernetes/AWS platform with event-driven systems

Required profile

• Hands-on experience building agents in production with agent SDKs (e.g. Claude Agent SDK, Codex SDK)
• Experience building and running MCP servers and tools
• Strong Python; English at B2 Upper Intermediate level

Required skills

• Deep hands-on Kubernetes (EKS preferred): cluster design, networking (CNI, service mesh), RBAC and security policies
• Strong AWS: VPC architecture, IAM, EKS/ECS, networking and security groups
• Infrastructure as code (Terraform, CloudFormation or Pulumi), GitOps and CI/CD (ArgoCD, GitHub Actions, Jenkins)
• Event-driven systems: queues and pub/sub (SQS, Kafka), webhooks, async workers, retries and idempotency
• Production observability and incident response (Datadog or similar)
• Nice to have: A2A protocols and multi-agent orchestration, JavaScript/TypeScript and Go, OAuth 2.0/OIDC, agent evaluation, permission-aware search, securing autonomous AI workloads, financial or regulated environments