Member of Technical Staff, Research Scientist - AI Safety & Security
$275kPlato
Job Description
Job Description
About Plato
Plato is an applied research lab building the foundational infrastructure to train specialized AI agents.
We turn real-world data streams into high-fidelity simulated environments that generate the training signal needed to make capable models. Our work supports frontier labs, hyperscalers, and enterprises building AI systems for complex, high-stakes work.
Today, only a handful of players can train models for capable work. Compute and algorithms are rapidly commoditizing, but reinforcement learning data remains the bottleneck. Plato is changing that by automatically scaling training environments from proprietary real-world data.
Why Apply-
Work with the frontier: Build safety environments and benchmarks that research teams at leading AI labs can use to measure emerging capabilities and misaligned behavior.
-
Real ownership: Help set Plato’s safety evaluation agenda, from the research questions worth testing to the evidence we share with lab partners.
-
Research to production: Work with engineers to turn experimental designs into runnable environments, with a short path from an idea to an evaluation labs can use.
Plato is hiring an individual contributor researcher to design safety environments and benchmarks, starting with evaluations that measure how well AI models can improve themselves and other models.
You will establish a new research direction at Plato, designing safety-relevant benchmarks and working with engineers to turn them into runnable environments. Your initial focus will be measuring AI R&D capabilities, including experiment design, model training, and research replication.
You will also investigate reward hacking, sabotage, deception, and other misaligned behavior. The work spans research design, empirical evaluation, and failure analysis, with substantial ownership of the research agenda. Some environments may also be used in training to reduce the behaviors they reveal.
What You’ll Do-
Design Safety Benchmarks: Measure AI research automation and self-improvement. Define tasks, baselines, budgets, and success criteria that separate meaningful progress from superficial completion.
-
Build Safety Environments: Design environments that expose reward hacking, sabotage, deception, and failures to follow intended constraints.
-
Hold the Evaluation Bar: Investigate contamination, grader weaknesses, task ambiguity, and shortcuts that could make a result misleading.
-
Track Frontier Capabilities: Run experiments with current models, inspect trajectories and failures, and measure how capabilities change across models and over time.
-
Work with Engineering: Turn research designs into reproducible environments with clear scoring, useful instrumentation, and documented limitations.
-
Share the Findings: Translate results into benchmark releases, research reports, and concrete recommendations for lab partners.
-
Recent Research: Hands-on work in frontier-model evaluation, benchmarks, or AI safety in the past one to two years.
-
Research Track Record: Meaningful contributions to papers, released benchmarks, public reports, or comparable empirical work. We care about the quality of your work and your contribution more than credentials or years of experience.
-
Current Model Knowledge: Practical familiarity with current frontier models and a specific, evidence-based view of their capabilities, limitations, and likely development.
-
Experimental Judgment: You can explain what an evaluation measures, how it could be gamed, and which conclusions its results do and do not support.
-
Research Ownership: Ability to turn an ambiguous question into a concrete experimental design and collaborate closely with engineers to implement it.
-
Safety Focus: Interest in measuring safety-relevant capabilities and behavior, including the tradeoffs when evaluation environments are also used for training.
-
Bay Area Based: Based in the San Francisco Bay Area, or willing to relocate.
-
Designed and released a benchmark, particularly for AI R&D, long-horizon agents, dangerous capabilities, or AI control. Relevant reference points include RE-Bench, MLE-bench, and PaperBench.
-
Experience in an independent evaluation or safety organization, a frontier lab safety team, or pre-deployment testing with labs or government evaluation bodies.
-
Direct research on models conducting ML experiments, training or improving other models, replicating papers, or completing extended research tasks.
-
A software engineering background or programming skills that let you implement environments, evaluation harnesses, and analysis tools yourself.
-
Experience publishing rigorous empirical research, including work at major machine-learning venues.
-
Prior experince as an AI Safety & Security Resaercher or AI Alignment Engineer or Researcher
Compensation Range: $275K - $450K
- ...Job Description Job Description Our client, an AI healthcare software startup, is seeking a Member of Technical Staff (Research Scientist) to join their team. In this role, you'll be at the forefront of developing benchmarks and evaluation methodologies for large...SuggestedH1bRelocation
$210k - $350k
...About Us Edison Scientific builds and deploys AI scientist agents to accelerate science and the development of new medicines... ...physics, chemistry, and AI. About the Role As a Member of Technical Staff, AI Research Scientist at Edison Scientific, you play a central...SuggestedFull timeWork at office$250k
...General Analysis is an AI safety and security research lab building guardrails, red-teaming frameworks, evaluations and runtime protection for AI... ...ICML, ICLR or similar are a plus. ~ High agency, strong technical acumen and clear thinking. Compensation: $250K – $4...SuggestedFull timeH1bWork at office- ...biological progress, not fundamental categories. We develop the AI systems that design modular biological machines — and the... ...and pick up whatever the problem needs. The role We want researchers with great intuition in machine learning and solid fundamentals...SuggestedFull time
- ...About the Team We’re a small team of researchers and engineers from MIT, Stanford, CMU, MosaicML... ...takes. The Role As a Research Scientist at Phonic, you'll drive original... ...the boundary of what's possible in voice AI. You'll own research directions end-to-end...SuggestedFull timeWork at office
$192k - $260k
...world's best and most secure platform for data and AI. We innovate and deploy... ..., and governance. As a member of the Trust and Safety Data Science team, you... ...engineering teams build highly technical products that fulfill... ...of “full stack” data scientists who partner with...Local areaWorldwide$150k - $220k
# Founding Member of Technical Staff (MTS)Bay Area, CAFull-time$150k... ...About UsVizopsAI is the secure runtime for custom... ...production layer that turns AI-generated internal... ...combines deep AI/ML research leadership at Google... ..., latency, cost, safety) into measurable signals...$200k - $300k
...Description Job Description Why work at Higgsfield AI? We're the fastest-scaling generative AI company in... ...Role Overview Higgsfield AI is looking for a hands-on Member of Technical Staff, Infrastructure Security to build, secure, and operate the systems that protect...Work at officeRemote workWorldwide3 days per week$300k - $400k
...Member of Technical Staff - Applied Scientist I Reinforcement Learning and Simulation Environments... ...Valley. We develop AI products for enterprises... ...blends reinforcement learning research with environment... ...checks, governed actions, safety constraints, and human-review...Remote jobFull timeWork experience placementLocal areaFlexible hoursShift work$300k - $400k
...Member of Technical Staff - Applied Scientist I Formal Methods for AI Driven Software Development Life Cycle San Francisco Bay... ...open-source contributions, and research partnerships in formal methods... ...collaborating with legal, compliance, safety, or domain experts....Remote jobFull timeWork experience placementLocal areaFlexible hours- ...spaces, and communications in one secure, integrated workplace... ...corporate headquarters, Envoy makes safety, security and associated... ...work on some of Envoy's most technically challenging and impactful products... ...from thousands of sources, uses AI to identify and enrich relevant...Full timeWork at officeLocal areaMonday to Thursday
- Perplexity's Secure Intelligence Institute (SII) seeks energetic researchers and engineers to advance security and privacy in frontier AI. You will identify threats, develop defenses, and build evaluation benchmarks for shipped AI systems. Publish findings at top venues...
$200k - $300k
...We have built the first AI simulation of society,... ...based on real humans. Our research pioneered the field of... ...About the Team The Security team is the guardian of... ...security, AI safety, and enterprise-grade privacy... ...procurement process , leading technical discussions regarding...Full timeFlexible hoursShift work- ...certify, and insure agents - working with AI category leaders like ElevenLabs, Lovable... ...We’ve built the gold standard for agent security & reliability, AIUC-1, with 100+ CISOs from... ...red-teaming evals DRI end-to-end: technical scoping, reconnaissance, execution, remediation...RelocationVisa sponsorship
- ...communications in one secure, integrated workplace management... ..., Envoy makes safety, security and associated... ...candidates typically come from staff or principal-level... ...for establishing technical direction, leading large... ...Experience applying AI-assisted tools or workflows...Full timeWork at officeLocal areaMonday to Thursday
- ...Mission Reflection is a research lab making intelligence... ...shape the future of AI. Our mission: make intelligence... ...failure modes across security, misuse, and alignment... ...team to translate safety findings into concrete... ...in AI Safety. Deep technical understanding of LLM safety...Full timeWork at officeVisa sponsorship
- ...are looking for an exceptional researcher to design and build the next generation of AI benchmarks for catching misaligned... ..., loss of control, multi-agent safety, etc. You will create high-impact... ...complex research ideas to both technical and non-technical audiences. NICE...Work experience placementRelocationRelocation packageShift work
- ...agent hosting (cloud VMs). Together, our technologies allow our customers to deploy AI agents at large scale to do the most challenging work. In this role, you'll focus on securing our service and infrastructure. You’ll work closely with the CTO and across our engineering...Full timeWork at office
- ..., iterate, and ship new products & functionality that solve security & safety problems in physical workplaces. Labs is a small and nimble... ...experience ~ BS / MS in Computer Science or a related technical field ~ Previous experience as a fullstack, product or frontend...Full timeWork experience placementWork at officeLocal area
- Perplexity is seeking energetic researchers and engineers to join our Secure Intelligence Institute (SII), Perplexity's flagship research center for advancing... ...intelligence. SII’s goals are to advance frontier AI security research, translate those advances into concrete...Remote work
$200k - $300k
...Why work at Higgsfield AI? Higgsfield AI is the fastest-scaling generative... ...AI is looking for a hands-on Member of Technical Staff, Product Security to identify and eliminate security... ...Offensive Security & Vulnerability Research Conduct hands-on penetration testing...Remote jobFull timeWork at officeWorldwide3 days per week$200k - $300k
...Why work at Higgsfield AI? Higgsfield AI is the fastest-scaling generative AI company in history, hitting $1B... ...Role Overview Higgsfield AI is looking for a hands-on Member of Technical Staff, Enterprise Security to own security across our corporate systems, employee...Remote jobFull timeWork at officeWorldwide3 days per week$200k - $300k
...Why work at Higgsfield AI? Higgsfield AI is the fastest-scaling generative... ...Higgsfield AI is looking for a highly technical, hands-on MTS, ML Security to join Higgsfield Security and own... ...in the San Francisco Bay Area . Team members are expected to work from our San Francisco...Remote jobFull timeWork at officeWorldwide3 days per week$150k - $300k
...count cells to accelerate cancer research, improve construction site safety , digitize floor plans , preserve... ...business that is exploding as AI traverses the physical economy. What You'll Do As a Member of Technical Staff on our Frontier Data team, you’ll...Full timeWork at office$200k - $400k
...mission is to grow vLLM as the world's AI inference engine and accelerate AI... ...the Role We're looking for a Member of Technical Staff, Product Security with deep infrastructure security expertise... ...Offensive security or security research experience that you turned into...Full timeRemote workVisa sponsorship- ...scaling simple methods across video games, real-world video, and our own fleet of affordable, durable robots. We're looking for research scientists who want to scale simple methods across the largest datasets available. You might be a good fit if you: Have...Full time
- ...Phylo is an applied research lab building... ...for every biomedical scientist. We believe AI agents will fundamentally... ...you’ll do as a Member of Technical Staff - Forward Deployed... ...preclinical) : nonclinical safety and toxicology,... ...-term financial security (US only) ~ Unlimited...Full timeWork at office
$164.7k - $339.08k
...Possible.At Pinterest, AI isn't just a... ...process here.As a Data Scientist in our Core... ...organization - Trust and Safety + Content Quality,... ..., Design, Research, Product Analytics... ...learnings to both technical and non-technical... ...those of a family member) or any other consideration...Work at officeLocal areaRelocationRelocation package- ...At Freed, an AI healthcare startup focused on reducing administrative burdens for clinicians... ...offering a collaborative environment where technical and product decisions shape the company's future. The Member of Technical Staff position involves full-stack product...
- ...Member of Technical Staff – Machine Learning I’m partnering with a rapidly scaling healthtech startup... ...to expand its engineering team. Their AI-powered platform is already helping... ...experience is a plus) ~ Background taking research ideas into production-ready services...Work at office
Do you want to receive more vacancies?
Subscribe and receive similar vacancies to Member of Technical Staff, Research Scientist - AI Safety & Security. Be the first to apply!
- helpdesk support technician San Francisco, CA
- tech assistant San Francisco, CA
- technical support assistant San Francisco, CA
- technical analyst San Francisco, CA
- desktop support analyst San Francisco, CA
- user support analyst San Francisco, CA
- support technician San Francisco, CA
- product support technician San Francisco, CA
- mri tech aide San Francisco, CA
- technical support analyst San Francisco, CA




