AI Safety Researcher: Frontier Cybersecurity Risks
United States Digital Space LLC
United States Digital Space LLC is seeking a Researcher for cybersecurity risks to design and implement an end-to-end mitigation stack across products, advancing safeguards as AI models evolve. You will work with cross-functional teams to span prevention, monitoring, detection, and enforcement, ensuring protections are scalable and low-latency as products and attacker behaviors evolve. Experience with deep learning, transformer models, and ML frameworks is required, with a strong focus on AI #J-18808-Ljbffr United States Digital Space LLC
Vacancy posted 4 days ago
Similar jobs that could be interesting for youBased on the AI Safety Researcher: Frontier Cybersecurity Risks in San Francisco, CA vacancy
- ...Preparedness is a critical Safety Research team at the company,... ...focused on mitigating AI threats to global... ...evolving capabilities of frontier AI systems.... ...As we push toward AGI, cybersecurity becomes one of the most... ...Researcher for cybersecurity risks, you will help design...Risk
- OpenAI is seeking a Researcher for Frontier Cybersecurity Risks to design and implement an end-to-end mitigation stack that reduces severe cyber misuse across OpenAI’s products. This role requires deep technical depth and close collaboration with risk, policy, product,...Risk
- OpenAI is seeking a cybersecurity risk researcher to design and implement an end-to-end mitigation stack to reduce severe misuse across OpenAI’s products. This role requires deep technical depth and close cross‑functional collaboration to ensure safeguards are enforceable...Risk
- A leading AI research organization is seeking a Researcher to focus on cybersecurity risks. The role involves designing and implementing mitigation strategies across products, ensuring effective safeguards as AI capabilities develop. Ideal candidates should have deep learning...Risk
- OpenAI is seeking a Researcher for cybersecurity risks to design and implement an end-to-end mitigation stack mitigating severe cyber misuse across our products. You will collaborate with cross-functional teams to ensure safeguards are robust, scalable, and effective as...Risk
- ...Team Preparedness is a critical Safety Research team at the company, which is focused on mitigating AI threats to global security... ...the evolving capabilities of frontier AI systems. Mitigation. Keeping... ...well as cyber and other frontier-risk areas), and maintaining...RiskPermanent employmentTemporary work
$320k
...interpretable, and steerable AI systems. We want... ...of committed researchers, engineers, policy... ...the Team The Frontier Red Team (FRT) is... ...researching and ensuring safety with self-... ...superhuman, in several cybersecurity domains. This is a... ...) to characterize risks, defensive...RiskWork at officeRelocationVisa sponsorshipFlexible hours- OpenAI in San Francisco seeks exceptional researchers to push the frontier of safety mitigations, helping derisk frontier models and advance techniques from... ...role requires deep technical experience, 2+ years in AI safety and a PhD or equivalent, plus 4+ years of research...
- ...Team Our Cyber team builds AI systems and products that... ...threats while improving the safety and reliability of frontier models in security-sensitive... ...with Safety/Preparedness, Research, Security, Legal, Communications... ...cyber use cases, evaluate risk, and turn feedback into...RiskFull time
OpenAI
San Francisco, CA11 hours ago - ...the real world. Mitigating the frontier risks resulting from these... ...evolving capabilities of frontier AI systems. Mitigation. Keeping... ...problematically misaligned, or their safety-relevant capabilities lag... ...rigorous hypothesis-driven research and turning our insights into...Risk
- Obsidian is seeking experienced AI Safety Red Teamers to identify vulnerabilities in frontier AI systems through adversarial testing. You will design... ..., and assess safety across high-risk topics. Join a cutting-edge research environment, collaborate with AI researchers...Risk
- United States Digital Space LLC in San Francisco is seeking exceptional research engineers to push the boundaries of frontier AI safety, shaping empirical understanding of risk and owning end-to-end threads within this effort. You’ll design evaluations of frontier models...Risk
- ...social engineering defense. Our AI-native platform uses agentic... ...simulation. By unifying Digital Risk Protection, Human Risk... ...defense. Our team combines deep cybersecurity expertise, operational rigor,... ...internet's most urgent trust and safety challenges.We're building the...Risk
Doppel
San Francisco, CA3 days ago - ...when the chain‑of‑thought of frontier reasoning models is monitorable... ...be a practical additional safety mechanism, and today our monitoring... ..., monitoring, and frontier‑risk research. We care most about... ...making increasingly capable AI systems more monitorable, trustworthy...RiskWork at officeRelocation package3 days per week
- ...world. Mitigating the frontier risks resulting from these capabilities... ...of frontier AI systems. Mitigation. Keeping... ...seeking exceptional researchers who can push the frontier of safety mitigations. You will help... ...such as misalignment, cybersecurity, and biology in order...Risk
$200k - $325k
...anything. We're building the AI that finally changes that. Ivo... ...deviation analysis to locate buried risk in huge contract databases [20... ...: Why, What, and Who Why AI Researchers are the engine of innovation... ...is to keep raising it. Push frontier techniques into production. Explore...RiskContract workWork at officeImmediate startRemote workVisa sponsorshipRelocation packageFlexible hours- ...important part of the Safety Systems org at OpenAI,... ...Preparedness Framework. Frontier AI models have the... ...pose increasingly severe risks. To ensure that AI promotes... ...(e.g., biosecurity, cybersecurity, and emerging risk... ...engineering, product, and research partners.Cybersecurity...RiskShift work
OpenAI
San Francisco, CA2 days ago - Anthropic is seeking a Capabilities Researcher to join the team building Claude Security. You will identify security capabilities in frontier models, measure performance, and ensure usability for non-experts. The role blends research with product impact, offering latitude...
$35 per hour
...we believe the safest AI is the one that’s already... ..., and flag systemic risks Apply structure: follow... ...(AI adversarial work, cybersecurity, socio-technical probing... ...Mercor customers trust the safety of their AI because you... ...AI red teaming at the frontier of safety Play a...RiskRemote job$162.7k - $263.18k
...Who We AreIn order to be the cybersecurity partner of choice, we must trailblaze... ..., and Inclusion. We weave AI into the fabric of everything... ....As a Principal Security Researcher, you will play a key... ...trailblazers that dream big, take risks, and challenge cybersecurity’...RiskFull timeWork at office- ...this role to work on site in the specified location(s).As an AI Researcher within Schwab’s AI Strategy & Transformation (AI.x) organization... ...closely with platform engineers, product partners, and risk stakeholders to ensure solutions are accurate, observable, safe...RiskFull timeWork at office
$139.6k - $225.78k
...Who We AreIn order to be the cybersecurity partner of choice, we must trailblaze... ..., and Inclusion. We weave AI into the fabric of everything... ...and self-driven Sr. Staff Researcher to join our Cloud-Delivered... ...trailblazers that dream big, take risks, and challenge cybersecurity’...RiskFull timeWork experience placementWork at officeVisa sponsorshipWork visa$180k
AI Engineer & Researcher - Safety & Societal Impact AI Engineer & Researcher - Safety & Societal... ...safety limitations of our frontier AI systems. You will improve our risk management framework and our... ...chemical security, biosecurity, cybersecurity, and nuclear safety....RiskFull timeFreelanceLocal areaRemote workRelocation- Numerai is hiring a senior quantitative researcher to expand the universe of signals and build robust risk models. You will develop alpha across horizons, work on covariance, factor risk estimation, and portfolio optimization, and ensure research becomes production-grade...Risk
$29 - $45 per hour
...technical talent with leading AI research labs. Headquartered in San... ...Jack Dorsey . Position: AI Safety Experts — English & Portuguese... ..., and flagging systemic risks. Apply structure by following... ...experience in AI adversarial work, cybersecurity, or socio-technical probing....RiskContract workSummer workRemote workMercor Inc
San Francisco, CA2 days ago$25 per hour
...technical talent with leading AI research labs. Headquartered in San... ...Dorsey . Position: AI Safety Experts — English & Indonesian... ..., and flag systemic risks. Apply structure using taxonomies... ...in AI adversarial work , cybersecurity , or socio-technical...RiskRemote jobContract workSummer workMercor
San Francisco, CA9 days ago$158.5k - $264.5k
...professional services operate. By combining frontier agentic AI, an enterprise-grade platform, and... ...looking for a seasoned strategic User Researcher to to join our research function. You... ...by surfacing unmet user needs, risks, and opportunities Push teams beyond validation...Risk$257k
...delivering increasingly capable AI systems requires... ...ownership of emerging risks, rigorous deployment... ...close coordination across research, engineering, product,... ...initiatives that turn safety commitments into deployed... ...misuse, child safety, cybersecurity, or other emerging threats...RiskFull timeWork at officeRelocation package- AI agents are changing how enterprises operate. Companies want to move fast with MCPs and agents, but they need a way... ...in real systems and turn that work into clear security research. Research agent security risks across tools, data access, identity, and MCP workflows....Risk
- ...operationalizes responsible AI governance at scale. We're a... ...seeking a Principal AI Security & Risk Researcher to join our founding... ...adversarial techniques, and model safety Security Framework Design:... ...For Required: 5+ years in cybersecurity, with 2+ years focused on AI...RiskPart timeRemote workFlexible hours
Do you want to receive more vacancies?
Subscribe and receive similar vacancies to AI Safety Researcher: Frontier Cybersecurity Risks. Be the first to apply!
Related searches
- postdoctoral researcher cosmetic science San Francisco, CA
- senior researcher San Francisco, CA
- researcher San Francisco, CA
- online researcher San Francisco, CA
- music researcher San Francisco, CA
- senior design researcher San Francisco, CA
- remote researcher San Francisco, CA
- product researcher San Francisco, CA
- security researcher San Francisco, CA
- field researcher San Francisco, CA