AI Red Teamer, Cybersecurity

Handshake; Seattle (WA); On-site; USD 120,000 - 210,000; Full time

Job summary

Handshake is seeking a Cybersecurity Red Teamer to evaluate whether AI models can be manipulated into generating malware, exploits, or attacker guidance. You will craft adversarial prompts and multi-turn interactions to simulate threat actor use of LLMs, then assess output risk and exploitability with deep cybersecurity expertise.

Day-to-day work includes designing prompts, evaluating model outputs for functional robustness, testing across multiple offensive categories, and collaborating with

Qualifications

• Experience in offensive security, penetration testing, red teaming, or incident response.
• Ability to read, write, and evaluate code across common languages used in offensive tooling.
• Understanding of MITRE ATT&CK, OWASP, and related frameworks.
• Ability to assess functional correctness and real-world exploitability of model outputs.
• Strong written and verbal communication for technical risk framing.

Responsibilities

• Design adversarial prompts to test AI models across cyber kill chains (reconnaissance to exfiltration).
• Evaluate model-generated code and outputs for functionality and exploitability.
• Test across malware, vulnerability exploitation, social engineering, credential harvesting, and exfiltration techniques.
• Probe dual-use boundaries and assess safe-guard effectiveness.
• Simulate attacker personas across skill levels to gauge risk escalation.
• Document findings with clear reasoning on what helps or harms attackers.

Skills

Offensive security

Penetration testing

Red teaming

Threat modeling

Adversarial thinking

Written communication

Education

Security certifications (OSCP/OSCE/GPEN)

Tools

Python

PowerShell

Bash

C/C++

LLM tooling

Job description

About Handshake

Handshake was founded on a simple belief that everyone deserves a path to a great career, regardless of where they went to school or who they know. Today, we power 25 million job seekers, 1 million+ employers, and 1,600 educational institutions.

About Handshake

Handshake was founded on a simple belief that everyone deserves a path to a great career, regardless of where they went to school or who they know. Today, we power 25 million job seekers, 1 million+ employers, and 1,600 educational institutions. In 2025, we started Handshake AI and built the fastest-growing AI data business in history. We work directly with frontier AI lab researchers to create evaluations, publish benchmarks, and push the boundary of data. We’ve grown from $0 to ~$1B run rate and pay ~$60M to over 30K individuals every month.

Why Join Handshake Now

• Shape how every career evolves in the AI economy, at global scale, with impact your friends, family and peers can see and feel
• Partner hand-in-hand with world-class AI labs, Fortune 500 partners and the world’s top educational institutions
• Work together with engineers, scientists, operators, and more from Palantir, Meta, Scale AI, and former YC founders
• Build a massive, fast-growing business with billions in revenue

About Handshake AI

Human data is the core infrastructure to AI advancement. Frontier AI labs currently improve model capabilities with various data-intensive post-training techniques. We believe that data spend for AI training will increase by 3-5x in the next few years and continue for much longer as models take on new domains. Handshake AI supports all of the frontier AI labs, working on their most complex data at the largest scale.

About The Role

As a Cybersecurity Red Teamer, you will evaluate whether AI models can be manipulated into generating functional malware, viable exploit code, attack tooling, or step-by-step operational guidance that would give a threat actor meaningful uplift in carrying out cyberattacks. Your job is to find the gaps between what a model's safety guardrails are supposed to block and what a skilled adversary can actually extract. This role requires you to think like an attacker who happens to have access to a very capable AI assistant. You will craft adversarial prompts and multi-turn interaction chains that simulate how real threat actors, from script kiddies to APT operators, might use LLMs to accelerate reconnaissance, weaponization, exploitation, lateral movement, persistence, and exfiltration. You will then evaluate whether the model's output is genuinely dangerous or just surface-level noise. Deep cybersecurity expertise is essential. The value you bring is the ability to look at a model-generated payload, exploit chain, or attack plan and assess whether it would actually work, how much refinement it would need, and what class of attacker it would meaningfully help.

Day-to-Day Responsibilities

• Design technically grounded adversarial prompts that test whether models provide meaningful uplift across the cyber kill chain (reconnaissance through exfiltration and impact)
• Evaluate model-generated code and technical output for functional correctness, assessing whether outputs represent real exploits, plausible attack tooling, or non-functional noise
• Test model behavior across offensive categories including malware generation, vulnerability exploitation, social engineering content, credential harvesting, privilege escalation, C2 infrastructure setup, and data exfiltration techniques
• Probe dual-use boundaries, testing how models handle queries that blend legitimate security research, penetration testing, and defensive operations with offensive applications
• Simulate attacker personas at varying skill levels (opportunistic, intermediate, advanced/APT) to assess how model risk scales with user sophistication
• Test multi-step and multi-turn attack chains, including scenarios where early turns establish benign context before pivoting to malicious requests
• Score model responses against structured harm taxonomies and severity rubrics calibrated to real-world exploitability
• Document findings with clear technical reasoning, including what a response gets right, what it gets wrong, and what level of attacker it would realistically assist
• Contribute to the development and refinement of cybersecurity-specific evaluation frameworks and threat models
• Collaborate with other red teamers, AI researchers, and policy teams to translate findings into actionable model improvements
• Stay current on evolving TTPs, CVEs, jailbreak techniques, and the intersection of AI and offensive security

Desired Capabilities

Core

• Professional experience in offensive security, penetration testing, red teaming, vulnerability research, malware analysis, threat intelligence, or incident response
• Ability to read, write, and evaluate code across common languages used in offensive tooling (Python, PowerShell, Bash, C/C++, JavaScript, or similar)
• Understanding of common attack frameworks, techniques, and procedures (MITRE ATT&CK, OWASP, etc.)
• Ability to assess the functional correctness and real-world exploitability of model-generated technical output
• Strong hands-on experience using multiple LLMs (ChatGPT, Claude, Gemini, open-source models, etc.)
• Creative, adversarial problem-solving skills
• Clear and precise written communication, including the ability to explain technical risk to non-specialist audiences
• Strong ethical judgment and the ability to separate adversarial thinking from personal values
• Self-directed, collaborative, and comfortable in feedback-heavy environments

Nice to Have

• Relevant certifications (OSCP, OSCE, GPEN, GXPN, CRTO, CRTL, CEH, or similar)
• Active or prior security clearance
• Experience with exploit development, reverse engineering, or binary analysis
• Background in cloud security, container security, or infrastructure-as-code attack surfaces
• Familiarity with AI/ML-specific attack surfaces (prompt injection, model extraction, training data poisoning, adversarial examples)
• Experience building or operating C2 frameworks, custom implants, or offensive tooling
• Bug bounty track record or published CVEs
• Prior work in trust and safety, content moderation, or AI evaluation
• Familiarity with LLM APIs or evaluation tooling

You Will Thrive Here If

• You have spent years breaking into systems and want to apply that mindset to breaking AI models
• You can look at a model-generated reverse shell, phishing template, or privilege escalation script and immediately tell whether it would land in a real environment
• You think in kill chains and attack graphs, not just individual prompts
• You understand that the difference between a helpful coding assistant and a dangerous one often comes down to context, specificity, and operational detail
• You follow the offensive security community closely and get excited when a new technique drops
• You care about AI safety because you understand what happens when powerful tools end up in the wrong hands

Content Warning

This role involves regular and deliberate engagement with offensive cybersecurity content. You will craft and evaluate scenarios involving malware, exploit code, social engineering, network intrusion techniques, and other attack methodologies. All work is conducted within a structured evaluation framework with strict ethical guidelines. Candidates must be able to engage with this material professionally, responsibly, and sustainably.