AI Red Teamer

πŸ•’ September 15

Where this job comes from

Posted on Handshake's careers page β†—Handshake's careers page, not through a job board

First seen by Remote Rocketship September 15

Still open on Handshake's site. Checked 3 hours ago.

Apply Now
Logo of Handshake

Handshake

501 - 1000 employees

Founded 2014

πŸ’Ό Consulting

πŸ₯ Healthcare

πŸ“¦ Logistics

Consulting β€’ Healthcare β€’ Logistics

Handshake is a platform that connects students with potential employers and career centers, offering tools to streamline the recruiting process for its users. It provides features such as job postings, talent engagement suites, and event management for both virtual and in-person recruiting events. Handshake is widely used by Fortune 100 companies and offers integrations with existing automated tracking systems. It aims to build early career networks and supports a diverse range of Gen Z talent with a focus on improving hiring outcomes through proprietary data and advanced recruiting strategies.

πŸ“‹ Description

β€’ Craft creative prompts and multi-turn scenarios to stress-test AI guardrails across diverse risk categories β€’ Discover ways around safety filters, restrictions, and defenses using jailbreak, evasion, and prompt injection techniques β€’ Explore edge cases to provoke disallowed, harmful, or incorrect outputs β€’ Evaluate and score model responses against structured harm taxonomies and severity rubrics β€’ Document experiments clearly, including what was tried, why it was tried, and what it revealed β€’ Review and refine adversarial prompts generated by other team members β€’ Contribute to harm taxonomy development, calibration exercises, and inter-rater reliability work β€’ Collaborate with engineers, data scientists, and researchers to share findings and strengthen defenses β€’ Work with potentially disturbing content regularly, including violence, self-harm, hate speech, sexually explicit material, and child safety scenarios β€’ Stay current on jailbreaks, attack methods, and evolving model behaviors β€’ Stress-test text, image, voice, and agentic model capabilities as project needs require β€’ Support AI safety and model robustness for leading research labs

🎯 Requirements

β€’ Strong hands-on experience using multiple LLMs, including ChatGPT, Claude, Gemini, and open-source models β€’ Intuition for crafting adversarial prompts; familiarity with jailbreak or evasion techniques is a strong plus β€’ Creative, adversarial problem-solving skills β€’ Clear and thoughtful written communication β€’ Strong ethical judgment and ability to separate adversarial thinking from personal values β€’ Self-directed, collaborative, and comfortable in feedback-heavy environments β€’ Curiosity, persistence, and comfort with frequent failure in experimentation β€’ Familiarity with Python or other scripting languages β€’ Experience working with LLM APIs or evaluation tooling β€’ Comfort with structured data annotation and rubric-based scoring β€’ Prior work in trust and safety, content moderation, QA, or security research β€’ Subject matter expertise in a high-risk domain such as cybersecurity, chemistry, biology, medicine, law, or finance β€’ Ability to work remotely from the United States, Monday through Friday, 40 hours per week β€’ Authorization to work lawfully in the United States for Handshake β€’ Ability to engage with harmful content professionally and sustainably β€’ California residents are ineligible for this role

πŸ–οΈ Benefits

β€’ Support resources are available for exposure to disturbing content β€’ W-2 employment through TCWGlobal

Apply Now

πŸ“Š Check your resume score for this job

Improve your chances of getting an interview by checking your resume score before you apply.

Similar Jobs

πŸ•’ September 14

Finance of America

501 - 1000

πŸ›‘οΈ Insurance

πŸ’Έ Finance

🏦 Banking

AI security leader safeguarding reverse-mortgage technology at Finance of America. Building controls, testing AI systems, and managing enterprise security risk.

πŸ•’ September 14

EY

10,000+ employees

πŸ₯ Healthcare

βš–οΈ Legal

πŸ“£ Marketing

EY consulting manager leading AI-enabled vulnerability management and continuous threat exposure programs. Advising enterprise clients on AI governance, risk prioritization, remediation, and security metrics.

πŸ•’ September 12

Workana

51 - 200

πŸ‘₯ HR Tech

πŸͺ Marketplace

🎯 Recruiter

AI web scraping engineer building stealth, self-healing scraping systems for Pinwheel API. Integrating anti-bot countermeasures, distributed infrastructure, and LLM parsing for US employment-data services.

πŸ•’ September 10

Wpromote

201 - 500

πŸ“£ Marketing

Director of AI Solutions at Wpromote, a digital marketing agency, building production AI systems and Polaris IQ integrations. Leading client-facing automation and developing AI talent.

πŸ•’ September 10

Blend360

501 - 1000

πŸ₯ Healthcare

🏨 Hospitality

✈️ Travel

Senior sales leader driving net-new enterprise revenue for Blend, an AI services provider, through OpenAI consulting and implementation engagements. Building strategic pipeline and closing complex North American accounts.

Built byΒ Lior Neu-ner. I'd love to hear your feedback β€” Get in touch via DM or support@remoterocketship.com
Follow Remote Rocketship on LinkedInFollow Remote Rocketship on InstagramFollow Remote Rocketship on FacebookFollow Remote Rocketship on TikTok