AI Platform Engineer, Agentic Engineering

About this role

Brain Co. seeks an AI Platform Engineer to build foundational infrastructure enabling agentic workflows across the company and production deployments. You'll own LLM integration layers, orchestration, security, and developer-facing abstractions that every team depends on.

What you'll do

• Design and operate LLM cost controls, data privacy, identity/access management, and security across provider traffic
• Build sandboxing, orchestration, audit, and guardrail layers for agent deployments with prompt-injection defenses and multi-tenant isolation
• Architect orchestration and resource models including cold-start vs. always-on tradeoffs, credential lifecycle, and quota enforcement
• Enable AI-assisted development as a platform layer with coding agents, CI automation, and code refactoring at scale
• Provide end-to-end ownership including architecture, implementation, rollout, observability, and incident response
• Partner with security and infrastructure teams to make agent systems safe by default

What they're looking for

• Backend systems design with 5+ years production experience (Python, TypeScript, Go, or Rust)
• Distributed systems fundamentals (consistency, idempotency, retries, scheduling, queueing)
• API and service design with proven internal platform adoption
• Cloud-native infrastructure (Kubernetes, infrastructure-as-code, OAuth/OIDC, secrets management)
• Observability and operational responsibility (SLOs, incident response, monitoring)
• LLM infrastructure experience (gateways, routing, cost attribution, evaluation)
• Agent frameworks and sandboxed code execution
• Security expertise including prompt injection defense and supply chain considerations