AI Safety Red Teamer (Train AI Models Part Time!)
Mercor
hackajob is collaborating with Mercor to connect them with exceptional professionals for this role. We are seeking experienced **AI Safety Red Teamers** to identify vulnerabilities in frontier AI systems through adversarial testing. You will design challenging prompts, uncover model weaknesses, and evaluate AI behavior across complex, high-risk, and ambiguous (\"grey-area\") topics. ## Responsibilities - Design adversarial prompts to stress-test frontier AI models. - Identify jailbreaks, unsafe behaviours, hallucinations, and policy failures. - Evaluate model robustness across misinformation, cyber, biosecurity, fraud, political content, and other sensitive domains. - Document vulnerabilities and contribute to safety benchmarking and red-teaming reports. - Collaborate with AI researchers to improve model alignment, robustness, and safety. ## Required Qualifications - Bachelor's degree or higher in Computer Science, Cybersecurity, Journalism, Communications, Psychology, Biology, Chemistry, Public Policy, or a related discipline. - 5+ years of professional experience in AI Safety, AI Red Teaming, Trust & Safety, cybersecurity, investigative journalism, life sciences, or a related field. - Strong analytical reasoning, prompt design, and written communication skills. - Experience designing adversarial prompts or evaluating frontier AI systems. ## Preferred Qualifications - Experience with AI Red Teaming, RLHF, SFT, AI Alignment, or Trust & Safety. - Familiarity with jailbreak testing, prompt engineering, or adversarial evaluation methodologies. - Expertise in one or more grey-area domains, including cyber, biosecurity, political content, misinformation, or scientific safety. ## Why Join?- Help secure and strengthen the next generation of frontier AI models. - Work on cutting-edge adversarial testing alongside leading AI researchers and safety teams. - Influence how AI systems respond to complex, real-world safety challenges.
Vacancy posted 10 hours ago
Similar jobs that could be interesting for youBased on the AI Safety Red Teamer (Train AI Models Part Time!) in New York, NY vacancy
- ...At Mercor, we believe the safest AI is the one that’s already been... ...attacked — by us. We are assembling a red team for this project - human data experts who probe AI models with adversarial inputs, surface... ...- Mercor customers trust the safety of their AI because you’ve...Part timeRemote work
- ...At Mercor, we believe the safest AI is the one that’s already been... ...attacked — by us. We are assembling a red team for this project - human data experts who probe AI models with adversarial inputs, surface... ...- Mercor customers trust the safety of their AI because you’ve...Part timeRemote work
- Mercor is seeking an AI Safety Red Teamer for a remote contract role. You will design adversarial prompts to stress-test frontier AI models, identify jailbreaks and unsafe behaviors, and evaluate robustness across sensitive domains. Join a team focused on documenting vulnerabilities...SuggestedRemote jobContract work
$70 - $84 per hour
...creative and technical talent with leading AI research labs. Headquartered in San... ..., and Jack Dorsey . Position: AI Safety Red Teamer Type: Contract Compensation:... ...adversarial prompts to stress-test frontier AI models . Identify jailbreaks, unsafe...SuggestedContract workSummer workRemote workMercor
New York, NY2 days ago- ...Help make the next generation of AI-narrated audiobooks sound genuinely... ...narration slips, so the underlying models can be made better. This is remote, part-time work at roughly 20 hours per week... ...to Have - Prior experience on AI training-data, model-evaluation, or audio/QA...Part timeRemote work
- ...with Mercor to connect them with exceptional professionals for this role. Mercor is recruiting DevOps / Platform Engineer (Train AI Models Part Time!) to work on a research project for one of the world’s top AI companies. This project involves using your professional...Part timeHourly payFull timeContract workFor contractorsWork experience placementRemote work
$400k
Insurance Specialist (Train AI Models Part Time!) Remote Up to $400,000/ year Join a leading AI lab's cutting-edge GenAI team to be at the core of the AI revolution, where your expertise fuels the development of the most advanced Large Language Models. Overview: Join a...Part timeContract workRemote workWeekday work$151.2k - $189k
Scale's Red Team and Safety function stress-tests the most capable AI models in the world, and shapes how labs, governments... ...how leading labs train their models and how... ...based cyber security are part of the deal.Coordinate... ...salary range for this full-time position in the...Full timeScale AI
New York, NY5 days ago$110.7k - $379.2k
...Summary Research Engineer — Post-Training & Small Language Models (SLMs), Healthcare AI Three hundred fifty million... ...how each affects reasoning quality, safety, latency, cost, and reliability. •... ...-per-dollar. Evaluation, safety & red teaming • Design evaluation...Local areaVisa sponsorshipDeloitte
New York, NY5 days ago$35 per hour
...LLM Red Teaming Coach About... ...the age of AI. Working across... ...technical training, work-based learning... ...replicable models, and helping... ...of our time get made — look... ...heavily in AI safety and security,... ...amateur red teamers use in an ethical... ...This is a part-time, remote,...Part timeHourly payTemporary workH1bWork at officeLocal areaRemote workVisa sponsorshipBreak Through Tech
New York, NY2 days ago$17 - $25 per hour
...creative and technical talent with leading AI research labs. Headquartered in San... ...and Jack Dorsey . Position: AI Safety Experts — English & Vietnamese... ...Remote Role Responsibilities Red team conversational AI models and agents by conducting jailbreaks,...Contract workSummer workRemote work$50 - $70 per hour
...radiological professionals to audit how AI models respond to sensitive questions... ...of SuperAnnotate, delivering training data for many of the world’s... ...physicists and radiation safety officers, radiochemists, and... ...inspection, peer review) or AI red teaming is a strong plus....Remote jobTemporary work$65 - $70 per hour
...hour Join an advanced AI safety initiative focused on improving... ..., and help ensure AI models produce scientifically... .... Comprehensive training will be provided to familiarize... ..., grading, or red-teaming scientific or technical... ...start. Flexible, part-time engagement of 15-25 hours...Part timeHourly payWeekly payContract workFor contractorsH1bImmediate startRemote workVisa sponsorshipFlexible hoursWeekday work- ...using the data they generate to power the next generation of AI-driven infrastructure. They're looking for engineers experienced... ...structure for large-scale data pipelines that downstream ML models will train on **You're a strong fit if you:** - Work today as a Level...Part timeContract workImmediate start
$192k - $240k
Applied AI is where Datadog's ambitious AI... ...intelligent over time, and tools that help... ...latency, cost, and safety considerations. Drive... ...: large language models, retrieval-augmented... ..., product training, and career pathingAn... ...submit to Datadog as part of your application...Work at officeDatadog
New York, NY3 days ago- ...The research teams behind the best-known AI models come to Mercor for data judgment they can... ...analysts and data practitioners who want AI training and evaluation work, not a specific job... ...of posting and pulling a listing each time, we keep one open per field and draw from...Part timeOdd job
- ...vulnerability-reproduction and remediation tasks used to train and evaluate a frontier AI lab's models. You'll assess whether CVE reproductions are faithful,... ...escalation) • Experience designing or evaluating two-part verification logic (functionality tests +...Part time
- ...at the core of how the next generation of AI models learns to work in spreadsheets.** # 1\.... ...will directly elevate the quality of the training data behind the most advanced Large Language... ...at a leading technology company as part of their extended workforce. # 2\. Key...Part timeContract workWeekday work
- ...role. Evaluate the quality, correctness, and methodological rigor of applied machine-learning tasks used to train and evaluate a frontier AI lab's models. You'll assess experiment design, model-selection reasoning, and evaluation methodology — and provide clear, rubric...Part time
$48 - $62 per hour
...creative and technical talent with leading AI research labs. Headquartered in San... ...and Jack Dorsey . Position: AI Safety Experts — English & Dutch Type:... ...Remote Role Responsibilities Red team conversational AI models and agents by performing jailbreaks,...Contract workSummer workRemote workMercor
New York, NY16 days ago$48 - $62 per hour
...creative and technical talent with leading AI research labs. Headquartered in San... ..., and Jack Dorsey . Position: AI Safety Experts — English & Swedish Type: Contract... ...: Remote Role Responsibilities Red team conversational AI models and agents to identify jailbreaks, prompt...Contract workSummer workRemote work- ...About the Role Mercor is partnering with a leading AI research lab to train frontier models on high-quality clinical and biomedical reasoning. We're... ...output outperforms the other, citing clinical accuracy, safety, and quality of medical reasoning - Provide written...Part timeImmediate start10 hours per weekFlexible hours
- ...connect them with exceptional professionals for this role. ## About the Role Mercor is partnering with a leading AI research lab to train frontier models on rigorous accounting and financial-reporting reasoning. We're hiring Accounting Experts to evaluate and compare...Part timeImmediate start10 hours per weekFlexible hours
- ...this role. **Help a leading AI lab ensure its models respond to people with care,... ...role is for you. This is a part-time commitment of at least 20... ...have:** a background in AI safety, applied ethics, trust and safety... ...evaluating, annotating or red teaming AI systems. You don'...Part timeContract workWeekday work
- ...Operators to join our global team of AI model trainers. In this role, you will play a crucial part in shaping the intelligence of... ..., or computer systems (training will be provided). Excellent reading... ...preferred working hours. Part‑time and full‑time project opportunities...Part timeFull timeFreelanceRemote workFlexible hours
$110 - $125 per hour
...The research teams behind the best-known AI models come to Mercor for biotechnology judgment... ...listing for biotech scientists who want AI training and evaluation work, not a specific job... ...instead of posting and pulling a listing each time, we keep one open per field and draw from...Part timeOdd job- SME Careers, a fast-growing AI Data Services company and subsidiary of SuperAnnotate... ...Rust Engineer for remote AI data training. You will review AI-generated Rust code... ...provide expert feedback to improve model accuracy and safety. This is a fully remote contract role...Remote jobHourly payContract workFlexible hours
- AuraOne seeks a Bilingual Portuguese STEM Expert (PhD) for a remote AI Safety red-team track. Reviewers craft attack scenarios, document failure... ...team can patch gaps. Adversarial evaluation helps harden AI models before deployment. You’ll think like attackers, write rigorous...Remote job
- 10a Labs is seeking a Red Teaming Fellow to evaluate safety, security, and reliability of frontier AI systems. You will work with researchers and engineers to identify vulnerabilities... ..., contributing to evaluations of frontier models and AI-enabled systems with test design and...Remote job
$45 - $70 per hour
Behavioral Health Expert, AI Safety and Model Evaluation is a remote red-team track for stress-testing AI systems against adversarial prompts. Reviewers craft attack scenarios, document the failure mode, and pair each successful jailbreak with the rubric clause it violated...For contractorsRemote work10 hours per week
Do you want to receive more vacancies?
Subscribe and receive similar vacancies to AI Safety Red Teamer (Train AI Models Part Time!). Be the first to apply!
Related searches
- custodian part time New York, NY
- part time summer dog walker New York, NY
- java part time New York, NY
- ehs part time New York, NY
- certified nursing assistant part time New York, NY
- food safety part time New York, NY
- health part time New York, NY
- business management degree part time New York, NY
- immediate openings part time New York, NY
- tableau part time New York, NY