ai platform infrastructure engineer

The company’s partner is a top-tier hedge fund expanding an AI agent platform that runs more than 1,500 agents in production across the firm.

• Run and own the agents, MCP servers, tools, and Kubernetes/AWS platform with its underlying event-driven systems
• Build secure communication between agents, agents that manage other agents, shared memory with appropriate access controls, and evaluations that ensure reliability at scale

• Hands-on experience building production agents with agent SDKs, including tool use, context and memory, and prompting
• Experience building and running MCP servers and tools
• Deep hands-on Kubernetes experience, preferably EKS, including cluster design, networking, RBAC, and security policies
• Strong AWS experience, including VPC architecture, IAM, EKS/ECS, networking, and security groups
• Experience with infrastructure as code, GitOps, and CI/CD
• Experience with container architectures for multi-tenant, security-sensitive workloads
• Experience with event-driven systems, including queues, pub/sub, webhooks, async workers, retries, and idempotency
• Production observability and incident response experience
• Strong Python skills
• Будет плюсом: Agent-to-agent protocols and multi-agent orchestration, JavaScript/TypeScript and Go, UI/front-end experience, OAuth 2.0/OIDC, identity federation and SSO, delegated tokens, agent evaluation, permission-aware search or retrieval, shared memory, securing autonomous or long-running AI workloads at scale, financial or regulated environments, compliance-aware infrastructure

• Условий в вакансии нет