AI Platform Engineer, Agentic Engineering

Brain Co.
San Francisco
Workplace: HybridFull timeFunction: DevOps, Cloud & InfrastructureSkills: ["Ownership","Product-grade engineering","Developer experience","Maintainability","Incident response"]

Build and scale the foundational platform layers that enable agentic workflows across the company’s AI-native operating systems. Own systems for LLM usage foundations—privacy, identity/access, routing, cost controls, isolation, orchestration, audit/guardrails, and observability. Tackle prompt-injection defenses and multi-tenant safety, partner with security/infrastructure/product, and drive end-to-end ownership from architecture through rollout, on-call, and adoption.

Loading

Loading job details...

Preparing the role view and application actions.

FursaFursa
Brain Co.
Brain Co.
3 months ago

AI Platform Engineer, Agentic Engineering

✓ Verified Job

Canonical indexed version, validated from employer's careers page.

Source: Company careers pageValidated by: Fursa AI
Last checked: 4 hours agoStatus: Live

Job Summary

Build and scale the foundational platform layers that enable agentic workflows across the company’s AI-native operating systems. Own systems for LLM usage foundations—privacy, identity/access, routing, cost controls, isolation, orchestration, audit/guardrails, and observability. Tackle prompt-injection defenses and multi-tenant safety, partner with security/infrastructure/product, and drive end-to-end ownership from architecture through rollout, on-call, and adoption.
Location: San Francisco
Workplace: Hybrid
Employment Type: Full time
Job Function: DevOps, Cloud & Infrastructure
Seniority: Mid level

Key Responsibilities

  • •Own foundational systems for how LLMs are used across the company, including cost visibility/controls, privacy, identity and access, routing, and security posture.
  • •Design sandboxing, orchestration, audit, and guardrail layers so product teams can safely build agents without reinventing abstractions.
  • •Develop defenses and controls for prompt injection, scoped credentials, kill switches, runaway-cost controls, and multi-tenant isolation.
  • •Create orchestration/isolation/resource models (cold-start vs always-on, credential/token lifecycles, fan-out/fan-in, fairness/quotas, and observability for debugging).
  • •Drive end-to-end ownership: architecture, implementation, rollout, observability, on-call, and iterative improvements with internal user feedback.

Pay and Benefits

Perks:EquityMeal AllowanceCommuter Benefits401kMedicalDentalVisionPaid Leave

Key Requirements

  • •5+ years building backend systems in production with deep proficiency in at least one of Python, TypeScript, Go, or Rust.
  • •Strong distributed-systems fundamentals (consistency, idempotency, retries, failure modes, queueing, scheduling).
  • •Designed and operated APIs/services that other engineers depend on.
  • •Built shared infrastructure or developer-facing services that real users adopted.
  • •Comfort owning the full lifecycle: design docs, MVP shipping, hardening, and driving adoption.
Experience:Distributed systemsBackend systemsDeveloper platformsLLM infrastructureAgent toolingMulti-tenantRegulated deploymentsGovernment deploymentsOpen source
Skills:OwnershipProduct-grade engineeringDeveloper experienceMaintainabilityIncident response
Tech Stack:PythonTypeScriptGoRustLLMsLLM infrastructurePrompt routingKubernetesInfrastructure-as-codeOAuthOIDCSecrets managementCIObservabilityVM-level pod isolationAPIOAuth/OIDC

Company Brief

Brain Co.
Brain Co. builds agent-native operating systems for regulated institutions across government, health, insurance, finance, and enterprise. Its platform emphasizes secure deployment, workflow integration, and AI applications tailored to complex operational environments.
Industry: AI & Machine Learning
Growth: Growth Stage Startup
Headquarters: San Francisco, United States
Founded: 2026
WebsiteLinkedIn