Founding Engineer — AI Agent Security

Investment profile

Seed-stage company with fewer than 10 people in San Francisco building an adaptive security layer for autonomous AI agents.

As agents gain access to company data, credentials, and tools, permissions alone cannot determine whether an action serves the user’s goal. This team is building a runtime firewall that evaluates an agent’s intent, context, and actions, blocks harmful behavior, and learns from newly discovered attacks.

The team is highly technical and works closely together in person in San Francisco. Its systems already protect production agent workflows.

Why this role

This is a hands-on founding engineering role at the intersection of AI research and production systems.

The hard problem is making sound security decisions fast enough to intervene before an agent acts, then turning attacks and production evidence into better defenses. You’ll help decide which technical problems matter most and carry solutions from experiment through deployment.

What you’ll build

Own foundational parts of the system that protects AI agents as they read untrusted information, use tools, and act across real environments.

Your strongest area may be inference, model training, or agent harnesses. In each case, the work extends beyond a successful experiment: you’ll build evaluations, ship reliable systems, observe how they perform, and improve them from real results.

You’ll work directly with the founders on technical direction and execution.

What you’ll work on

• Low-latency models and inference systems for runtime security decisions
• Evaluations that measure harmful behavior, false positives, latency, and reliability
• Autonomous red-team agents and attack-generation harnesses
• Training data and learning loops built from verified attacks and production outcomes
• Systems that reason across user intent, encountered content, tool calls, and an agent’s sequence of actions
• Production architecture, observability, isolation, deployment safety, and recovery
• AI-native engineering workflows that increase output while preserving rigorous review and testing

What they’re looking for

• Strong software engineering fundamentals and a clear contribution to systems shipped into production
• Depth in at least one of inference optimization, model training and evaluation, or harness engineering
• Ability to take an ambiguous technical problem through hypothesis, experiment, implementation, and operation
• Judgment about correctness, latency, and reliability when the system’s decisions have real consequences
• Comfort moving between research and engineering rather than stopping at a prototype
• Initiative and clear communication in a small team where priorities evolve quickly

Strong signals

• Built and operated an AI, ML, or agent system used in production
• Improved model capability, inference performance, or evaluation quality with measurable results
• Built tooling that exposes failures in agent behavior or makes experiments repeatable
• Helped turn an unclear technical problem into a working product or durable system
• Uses coding agents, automated evaluation, testing, and review to expand engineering output without losing command of the underlying work

Security experience is valuable, but direct experience in agent security is not required.

Level and experience

This is a hands-on individual contributor role. The team will consider experienced engineers and exceptional earlier-career builders. The strength, scope, and results of the work you’ve done matter more than a particular title or number of years.

The role is based in San Francisco and is intended for someone who wants to build closely with the team in person.

About Us

Greylock is an early-stage investor in hundreds of remarkable companies including Airbnb, LinkedIn, Dropbox, Workday, Cloudera, Facebook, Instagram, Roblox, Coinbase, Palo Alto Networks, among others. More can be found about us here: https://greylock.com/

How We Work

We are full-time, salaried employees of Greylock and provide free candidate referrals and introductions to our active investments. If your background looks like a potential match, we’ll contact you to schedule a call.

Due to the selective nature of this service and the volume of applicants we typically receive from our job postings, a follow-up email will not be sent until a match is identified with one of our investments.

Please note: We are not recruiting for any roles within Greylock at this time. This job posting is for direct employment with a startup in our portfolio.