About Hamming
Hamming is the security layer for voice and chat agents. Banks, health systems, and other enterprises are putting agents on phone lines where anyone can reach them, and where the agent can verify identity, read an account, and act. We attack those agents before criminals do, with the owner's permission, show what they fall for, and keep every fix tested on every release.
We are one of the fastest engineering teams in the world. We prod deploy 4x / day.
OpenAI Dev Day 100billion token list
The role
You run authorized assessments of production voice and chat agents at banks, health systems, and other enterprises. You scope the engagement with the owner, run it through a harness that makes thousands of calls, decide which results are security failures with a real consequence, and write the finding the owner fixes the same day. Then you rerun it, because a fix is a claim until the same attack fails again. Findings become permanent tests; the work you can share goes out through responsible disclosure and on stage.
What you'll do
Own the assessment. Threat model, scope, test identities, stopping conditions, and the evidence a finding needs.
Follow the whole path. Conversation, retrieved content, identity checks, and tool permissions, to the point where the agent crosses a line.
Work carefully in production. Approved scenarios, controlled data, the customer informed, a hard stop at the agreed limit.
Prove what's exploitable. Preconditions, reproduction, impact, and the fix, with severity stated honestly.
Verify the remediation. Turn the case into regression coverage, and teach the harness what you found by hand.
What you'll bring
5+ years in offensive security, with authorized assessments of production applications, APIs, or agent systems.
Hands-on AI attack work: prompt injection, jailbreak chains, tool and function-call abuse, data exfiltration through model outputs.
Application security fundamentals: authentication and authorization bypass, injection, session and identity handling.
Reports a developer can reproduce and a CISO can defend, and Python or TypeScript to make your work repeatable.
Nice to have
Assessments of voice or telephony systems
Engagements with banks or health systems
Published research, a CVE, or a conference talk
How we work
We start with the customer problem, ship daily, and let evidence decide what comes next. Use AI tools to move faster and own the result. Direct, low ego, serious work.
Benefits and perks
Competitive salary and meaningful equity
Health, dental, and vision coverage
Every frontier AI tool, fully paid, from day one
Conferences and events we sponsor
Flexible PTO
Offices in San Francisco and Austin; remote in the United States for most roles