AI Platform Engineer, Agentic Engineering

brainco

San Francisco (CA)

On-site

USD 120,000 - 160,000

Full time

14 days+

Get more replies from employers

Send a job-specific resume in minutes.

Benefits offered by this job

Competitive salary plus equity

Daily lunches

Commuter benefits

401(k)

Medical, Dental and Vision

Unlimited PTO

Job summary

BrainCo in San Francisco is hiring for a pivotal role focused on building foundational systems that enable agentic workflows across the company. You will be integral in developing platforms that are used by every engineering team, ensuring the company’s productivity and efficiency across various sectors.

Ideal candidates have a strong background in backend systems and distributed architectures, with a genuine commitment to innovation in AI applications. Join us to shape the future of AI!

Qualifications

5+ years building backend systems in production.
Strong fundamentals in distributed systems.
Experience designing and operating APIs.

Responsibilities

Own the foundations of LLMs across the company.
Design sandboxing and orchestration for product teams.
Solve challenges like prompt-injection defenses.

Skills

Backend systems

Python

TypeScript

Rust

Distributed systems

APIs

Developer experience

Cloud-native experience

Tools

Kubernetes

OAuth/OIDC

Infrastructure-as-code

Job description

About Brain Co.

Brain Co. is an applied AI startup co-founded by Jared Kushner and Elad Gil, and backed by leading Silicon Valley builders including Patrick Collison and Andrej Karpathy.

We are building AI applications for the world’s most important institutions, delivering impact on real-world problems across governments, healthcare systems, and critical industries.

Our progress so far:

Automated construction permitting for a sovereign government 80% faster, unlocking $375M+ in value
Optimized supply chains for a leading global energy company 30% lower cost, 99% reliability, preventing $100M+ in losses
Streamlined hospital patient care across national health systems 40% better outcomes, 80% less admin work

Company momentum:

Raised a $55M Series A from leading investors
Built a team of 70+ AI experts from Tesla, Google DeepMind, NVIDIA, and Databricks

At Brain Co., we focus on applying frontier AI to real institutional challenges, working alongside governments, healthcare systems, and critical industries to modernize how essential services operate.

We are looking for leaders who want to help bring new technology into institutions that impact millions of people.

About the role:

You'll join the team that builds and enables agentic workflows across Brain Co. For every engineer, operator, and business team internally, and for the production AI systems we deploy to governments, healthcare systems, and critical industries. This is a platform role at the center of the company's agent-first strategy: you'll build foundational systems used by every engineering team, and the bar is product-grade because the entire company depends on them.

What you’ll work on:

Own the foundations of how LLMs are used across the company: cost visibility and controls, data privacy, identity and access, routing, and the security posture around all provider traffic.
Design the sandboxing, orchestration, audit, and guardrail layers that product teams build their agents on, so verticals don't need to invent their own abstraction.
Solve the hard problems: prompt-injection defenses, scoped credentials, kill switches, multi-tenant isolation (including VM-level pod isolation), and runaway-cost controls.
Design the orchestration, isolation, and resource models that make this viable: cold-start vs. always-on tradeoffs, credential and token lifecycle, fan-out and fan-in patterns, fairness and quota enforcement across tenants, and the observability needed to debug at that volume.
Make AI-assisted development a first-class platform layer: coding agents that review and ship code, automate CI, refactor at scale, and run as background workers across the codebase, together with the canonical scaffolding and guardrails that govern them.
Build the systems that let every team; engineering, operations, and the business, run their own agents reliably and safely against the tools they already use, with the right credentials, scheduling, memory, and audit underneath.
End-to-end ownership: architecture, implementation, rollout, observability, on-call, and iteration based on internal user feedback.
Partner closely with security, infrastructure, and product teams to make agent deployments safe by default.

You Might Be a Great Fit If You…

Have 5+ years building backend systems in production, with deep proficiency in at least one of Python, TypeScript, Go, or Rust.
Bring strong fundamentals in distributed systems: consistency, idempotency, retries, failure modes, queueing, scheduling.
Have designed and operated APIs and services that other engineers depend on.
Have a proven track record building shared infrastructure, internal platforms, or developer-facing services that real users adopted.
Have strong intuition for developer experience, long-term maintainability, and where to draw abstraction boundaries.
Are comfortable owning the full lifecycle: writing the design doc, shipping the MVP, hardening it, and driving adoption across the company.
Have owned services with real uptime and operational responsibility, and are comfortable with observability stacks, incident response, and SLOs.
Bring cloud-native experience: Kubernetes, infrastructure-as-code, OAuth/OIDC, secrets management.

Ways you might stand out:

Experience building or operating LLM infrastructure: gateways, inference systems, prompt routing, cost attribution, evaluation harnesses.
Experience with agent frameworks, tool-use systems, or sandboxed code execution.
Security instincts around prompt injection, supply-chain risk in agent ecosystems, and credential scoping for autonomous systems.
Background in multi-tenant, regulated, or government deployments (HIPAA, SOC2).
Open-source contributions to AI infrastructure, agent tooling, or developer platforms.

Why Join Us