Red Team Engineer — AI Safety & Adversarial Testing (Flexible Hours)
Doist
Anthropic is seeking a Red Team Engineer to uncover vulnerabilities across our AI product ecosystem. You will simulate adversaries, perform comprehensive adversarial testing, and explore novel abuse vectors in our deployed systems. You will design kill-chain style attacks, build automated testing frameworks, and collaborate with Product, Engineering, and Policy teams to translate findings into concrete improvements for safer AI. #J-18808-Ljbffr Doist
Vacancy posted 2 days ago
Similar jobs that could be interesting for youBased on the Red Team Engineer — AI Safety & Adversarial Testing (Flexible Hours) in San Francisco, CA vacancy
$300k - $405k
...steerable AI systems. We... ...whole. Our team is a quickly... ...researchers, engineers, policy... ...build the safety and oversight... ...up against adversarial pressure in... ...Design and run red-teaming and stress-testing of... ...bias towards flexibility and impact... ...flexible working hours, and a...Flexible hoursWork at officeVisa sponsorshipShift work$182k - $238k
...translate compute into safety at scale. Red-teaming previously sat... ...owner. As the AI Red Team Engineer, you will help build... ...that haven't been tested against yet and... ...attacker and want your adversarial findings to... ...salaries soon. Flexible work hours and schedule Unlimited...Flexible hoursFull timeWork at officeWork from homeVisa sponsorshipRelocation packageApollo Research
San Francisco, CA4 days ago- Anthropic’s Safeguards team is seeking a Red Team Engineer to help ensure the safety of our deployed AI systems and products. You will take an adversarial approach to uncover vulnerabilities across our product ecosystem before they can be exploited by malicious actors....Suggested
- Reflection is seeking a highly skilled safety researcher to own red-teaming and adversarial evaluation for our open-weight models. You will probe for failure modes... ...as a gatekeeper for model releases, balancing risk with ambitious AI capabilities. #J-18808-Ljbffr Visa HuntSuggested
- B Capital in San Francisco is looking for individuals passionate about AI safety to own the red-teaming and adversarial evaluation pipeline for their models. The role involves collaborating with the Alignment team and ensuring all releases meet safety thresholds. Candidates...Suggested
$320k - $405k
...and steerable AI systems. We... ...whole. Our team is a quickly... ...researchers, engineers, policy... ...is seeking a Red Team Engineer... ...ensure the safety of our deployed... ...'ll take an adversarial approach to... ...adversarial testing across Anthropic... ...leave, flexible working hours, and a lovely...Flexible hoursWork at officeVisa sponsorship- ...hallucinated commitments. Build adversarial evaluations, simulations, red-team datasets, and regression... ..., identify root causes, test mitigations, and measure their... ...~4+ years of experience in AI/ML engineering, research, or AI safety. ~ Hands-on experience evaluating...Full timeWork at office
- ...We are searching for an AI Safety Specialist who will play a crucial... ...AI systems by conducting adversarial testing, implementing protective... ...Background in cybersecurity, prompt engineering, or adversarial ML.... ...jailbreak taxonomies and automated red-teaming frameworks. Strong...
Hyphen Connect Limited
San Francisco, CA18 hours ago - ...new medium, work with a small team that cares deeply about... ...entertainment company and the leader in AI music. We are backed by... ...Suno is hiring a Software Engineer, Trust and Safety, to be on the front lines of... ...~ Experience with A/B testing and experimentation in Trust...Full timeWork at officeLocal area
Suno
San Francisco, CA18 hours ago $180k
AI Engineer & Researcher - Safety & Societal Impact AI Engineer & Researcher - Safety &... ...pursuit of knowledge. Our team is small, highly motivated,... ...develop novel evaluations and red teaming mechanisms to... ...Session: This session will be testing your ability to formulate,...Full timeFreelanceLocal areaRemote workRelocation$267k
...Senior Staff Engineer (Backend) About the Role We’re looking for a... ...product, operations, and platform teams to define scalable backend systems... ...trip-lifecycle support, Agentic AI capabilities, and building reliable end-to-end testing and quality frameworks as AV...Full timeWork at officeRemote workUber
San Francisco, CA1 day ago$134.5k - $265.1k
...Trust and Online Safety ManagerThe Digital... ...the Deloitte Cyber team, you will be responsible... ...and executing testing scenarios to... ...injection, jailbreak, and adversarial testing techniques... ...intelligence red teaming, adversarial... ..., policy, and engineering stakeholders to translate...Local areaVisa sponsorship$196k - $294k
...shaped how the web is built. As the team behind Next.js, v0, and AI SDK, we create products that help... ...what comes next.As a Software Engineer on our Trust & Safety at Vercel, you’ll build and operate... ...build your network and skills. Flexible Time Off. We will provide you the...Flexible hoursWork at officeRemote workWork from homeWorldwideMonday to Friday$248k - $310k
...spending a combined 1.5 billion hours playing thousands of... ...for a Staff Software Engineer to join our Safety Processing team. This team plays a crucial... ...Implement and enhance ML/AI models and automation to... ...Build solutions with an adversarial mindset, anticipating and...Full timeRelocationRelocation packageDiscord
San Francisco, CA18 hours ago$200k - $245k
...intelligence (AI) powered... ...to develop, test and deploy autonomous... ...'s the core engineering challenge of... ...per 10⁸ hours of operation.... ...that level of safety and proving it... ...to join the team. This will be... ...physical systems — adversarial search,... ...Insurance Flexible PTO, 10 paid...Flexible hoursTemporary workWork at officeVisa sponsorshipKodiak
San Francisco, CA3 days ago- Xcede is looking for a Member of Technical Staff focused on AI Safety to lead red-teaming efforts and ensure the robustness of next-generation AI... ...have deep expertise in LLM safety, strong software engineering skills, and relevant academic qualifications in AI or related...
$225k - $250k
..., we started Handshake AI and built the fastest-growing... ...Work together with engineers, scientists, operators,... ...sophisticated Trust & Safety surface area: KYC and... ...Build out a robust and flexible payment and incentives... ...operations that let our ops team run pay weeks safely....Flexible hoursFull timeContract workWork at officeHandshake
San Francisco, CA9 days ago$160k - $190k
...’re looking for a Senior Android Engineer to join our Trust and Safety engineering team. This team is responsible for developing... ...business impact. We follow a flexible hybrid model that generally... ...bases, including API design and unit testing techniques. Can collaborate with...Flexible hoursWork at officeWorldwide3 days per week$196k - $220.5k
...combined 1.5 billion hours playing thousands of... ...playing games. The Safety Processing team builds the infrastructure... ...a Senior Software Engineer who can take ownership... ...rotation. Apply an adversarial mindset to enforcement... ...stakeholders. Using Gen AI products, like Claude...Full timeRelocationRelocation package- Mercor is seeking an AI Safety Expert to remotely assess and fortify AI systems. You will red-team conversational models, identify jailbreaks... ...is essential, with prior adversarial or cybersecurity experience... ...offers remote work with flexible collaboration across time zones...Flexible hoursRemote jobContract work
$180k - $220k
A tech company in AI collaboration is seeking a backend engineer to build a scalable platform for team communication. This role requires 5+ years in backend development and... ...ranges from $180,000 to $220,000 annually, with flexible vacation policies. #J-18808-Ljbffr Glu...Flexible hours$315k
We are looking for Research Engineers to build “gold standard” evaluations... ..., in order to understand what AI Safety Level (ASL) to assign to models. Research leads on this team collaborate with engineers in... ...and tooling for testing for these capabilities, and iterating...Currently hiringWork at officeImmediate startHome officeVisa sponsorshipRelocation package$134.4k - $168k
...intelligence is embodied. The Physical AI team is focused on building general... ..., we are looking for a Safety Coordinator / Lab Lead to anchor our physical testing operations. Role Overview As the... ...will ensure our researchers, engineers, and autonomous systems interact...Full time$275k - $300k
...Operations. We are a team of builders,... ...team is the "red" pulse of this... ...we simulate the adversary to ensure our... ...security validation, AI-augmented... ...Offensive Security Engineer who is as much... ...in adversarial testing of AI systems,... ..., and a flexible schedule working...Flexible hoursWork at office3 days per week$196k - $220.5k
...after playing games. The Safety Processing team builds the infrastructure and... ...for a Senior Software Engineer who can take ownership of complex... ...-call rotation. Apply an adversarial mindset to enforcement... ...Operations stakeholders. Using Gen AI products, like Claude Code,...Full timeWork at officeRelocation package2 days per week- ...-demand, logistics engine for delivery. We are... ...our engineering teams to build exciting featuresImprove... ...with Android testing best practices and... ...Regarding Use of AI and Automated Tools... ...salaried roles: flexible paid time off/vacation, plus 80 hours of paid sick time per...Flexible hoursHourly payWork at officeLocal areaRemote work
$174k - $252k
...techniques to understand what AI systems are thinking.Work with product teams to ensure that our... ...Science, a related Software Engineering field, or equivalent... ...research to improve the safety and alignment of frontier... ...to setup large-scale tests and deploy promising ideas...- ...The Data Platform team spans data mobility... ...data workflows for engineers, analysts, and ML practitioners... ...in using AI coding tools (e.g.,... ..., generating code, testing, monitoring and... ...For salaried roles: flexible paid time off/vacation, plus 80 hours of paid sick time per...Flexible hoursHourly payWork at officeLocal areaRemote workRelocation
$180k - $310k
...Why this role matters now AI has dramatically lowered the barrier... ...side. A small, sharp T&S team equipped with frontier models... ...magical. As a Trust & Safety Engineer, you'll architect the systems... ...creative and connected, with flexibility to work from home when focus...Full timeWork at officeWork from homeGamma
San Francisco, CA18 hours ago- ...About the Team The Safety Systems team is dedicated to ensuring the safety, robustness, and reliability of AI models and their deployment in the real world. Learn more about OpenAI... .... That's why we're seeking a software engineer to help us build out our trust and safety...Full time
OpenAI
San Francisco, CA18 hours ago
Do you want to receive more vacancies?
Subscribe and receive similar vacancies to Red Team Engineer — AI Safety & Adversarial Testing (Flexible Hours). Be the first to apply!
Related searches
- public health engineer San Francisco, CA
- functional safety engineer San Francisco, CA
- safety engineer San Francisco, CA
- reliability and safety engineer San Francisco, CA
- senior safety engineer San Francisco, CA
- zillow flex San Francisco, CA
- flexible hours work from home San Francisco, CA
- security officer flex San Francisco, CA
- flex schedule San Francisco, CA
- flexible evening San Francisco, CA