AI Red Team Engineer

Hamming AI; Austin (TX); Remote; USD 120,000 - 180,000; Full time

Benefits offered by this job

Health, dental, and vision coverage

Competitive salary and equity

Access to frontier AI tools from day 1

Conferences and events sponsorship

Flexible PTO

Remote-friendly in the United States

Job summary

Hamming is hiring for a security-focused role in Austin, USA. You will own the harness that runs calls and chats, evaluate results, and replay changes across thousands of concurrent sessions with strong emphasis on evidence and reproducibility.

You’ll bring 3+ years building backend services in Python or TypeScript, plus an adversarial mindset and a focus on measurable, reusable findings across releases. Remote-friendly, with offices in SF and Austin.

Qualifications

• 3+ years building backend services, async workers, or test infrastructure in Python or TypeScript, with the failure cases and the tests.
• An adversarial mind: offensive tooling, CTFs, fuzzing, or a security project.
• Judgment about evidence: when an automated evaluator is enough and when a human has to look.
• Idempotency, backpressure, observability, and limits that are enforced rather than documented.

Responsibilities

• Build the attack harness.
• Generate useful variations.
• Make results trustworthy.
• Make findings reproducible.
• Keep fixes fixed.

Skills

Backend services

Python

TypeScript

Testing infrastructure

Job description

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.

The role

Our researchers find the failure by hand. You make it happen a thousand times, against authorized targets, with evidence a customer can inspect, and again on every release. You own the harness: the runner that places calls and chat sessions, the evaluators that decide what a result means, and the replay that shows what changed. Thousands of concurrent calls, bounded, cancellable, observable.

What you'll do

• Build the attack harness. A new technique is a new definition, not a new system.

• Generate useful variations. Branch multi-turn scenarios and voice conditions with the objective and conditions explicit.

• Make results trustworthy. A successful attack, a refusal, an infrastructure failure, and an inconclusive result are distinguishable and inspectable.

• Make findings reproducible. Scenario, configuration, model versions, tool events, outcome, replay, and comparison.

• Keep fixes fixed. Validated findings become regression tests that run on every change, with noise controlled.

What you’ll bring

• 3+ years building backend services, async workers, or test infrastructure in Python or TypeScript, with the failure cases and the tests.

• An adversarial mind: offensive tooling, CTFs, fuzzing, or a security project. The title does not matter.

• Judgment about evidence: when an automated evaluator is enough and when a human has to look.

• Idempotency, backpressure, observability, and limits that are enforced rather than documented.

Nice to have

• Agent frameworks, voice or telephony systems, or LLM evaluation infrastructure

• A security finding of your own, responsibly disclosed

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