AI Safety Scientist: Agent Robustness & Risk Evaluation
Scale
Scale Labs seeks a Research Scientist focused on Agent Robustness in a multi-location setting. You will tackle fundamental challenges in building safe AI agents and aligning them with humans, including benchmarking methods and mitigation strategies. Ideal candidates have 3+ years in ML research, a publications track record in ML, and experience with RLHF, DPO, or GRPO, plus strong cross-functional communication. Some familiarity with agent evaluation tooling is a plus. #J-18808-Ljbffr Scale
Vacancy posted 22 hours ago
Similar jobs that could be interesting for youBased on the AI Safety Scientist: Agent Robustness & Risk Evaluation in New York, NY vacancy
- Scale Labs seeks a Research Scientist to advance agent robustness, safety, and alignment in frontier AI systems. You will develop evaluation harnesses, prototype inspired by research, and collaborate across teams to push practical ML solutions. We prioritize candidates...Suggested
- Scale Labs is seeking a Research Scientist focused on Agent Robustness to advance safe and aligned AI agents. You will contribute to evaluating risks, building testing harnesses, and prototyping mitigation strategies across agent interactions and environments. The role...Risk
- ...over 80 million customers.As an AI Agents Applied Research/Engineering... ...step planning, tool use, and safety; building production systems... ..., Engineering, Design, and Risk teams to bring those systems... ...batching, prompt governance, and evaluation frameworks.Implement privacy,...Risk
$216k - $270k
Scale Labs, Research Scientist - Agent Robustness As the leading data and evaluation partner for frontier AI companies, Scale plays an integral... ...scientific decisions about AI risks and capabilities. Our... ...focus on how they relate to safety, risk factors, and methodologies...RiskFull time$216k - $270k
Scale Labs, Research Scientist — Agent Robustness As the leading data and evaluation partner for frontier AI companies, Scale plays an integral... ...scientific decisions about AI risks and capabilities. Our... ...focus on how they relate to safety, risk factors, and methodologies...RiskFull time- Scale Labs seeks a Research Scientist focused on Frontier Risk Evaluations to design evaluation measures, harnesses and datasets for measuring risks posed by frontier AI systems. You will build harnesses to test models, collaborate with government agencies to scope evaluations...Risk
- Scale AI, Inc. is looking for a Research Scientist focused on Frontier Risk Evaluations to develop evaluation measures and datasets for assessing AI risks. As a key team member... ...and publish methodologies that influence AI safety policy. Candidates should have a strong track...Risk
$80 per hour
...Mindrift connects specialists with project-based AI opportunities for leading tech companies, focused on testing, evaluating, and improving AI systems. Participation is... ...focus on building React‑based interfaces and robust Back‑end systems Experience writing tests (functional...Permanent employmentTemporary work$175k - $250k
...to collaboration, disciplined risk management and continuous learning... ...Science team applies modern AI and machine learning... ...workflows.Conduct applied research to evaluate new AI and machine learning techniques... ...to measure model quality, robustness, reliability, and business...RiskFlexible hours- Rex.zone is seeking an AI Research Scientist to lead applied AI research projects for US-based customers... ...into measurable experiments in LLM evaluation and RLHF data design. You will... ...functional teams to improve model performance, safety, and usefulness. The role is remote in...Remote jobHourly payFlexible hours
$72k - $184.44k
...SummaryThe OpportunityAs an AI Data Scientist Senior Associate, you will leverage... ...- Designing and developing robust data solutions to transform... .../Technology Management, Risk Management/Insurance-... ...experimentation, and model evaluation techniques to develop and validate...RiskFull timeH1b- Google DeepMind is hiring a Research Scientist to lead governance research and risk modeling for the Frontier Safety Framework (FSF). You will drive research, model AI severe risks, and represent the program in governance discussions and model launch processes. The role...Risk
- Google DeepMind is hiring a research scientist to lead governance research and risk modeling for the Frontier Safety Framework (FSF). This role develops risk assessments for frontier AI and informs safeguards and deployment decisions. You will collaborate with policy and...Risk
$80 per hour
...collective human intelligence to ethically shape the future of AI. What We Do The Mindrift platform connects specialists... ...for someone who can design realistic and structured evaluation scenarios for LLM-based agents. You'll create test cases that simulate human-performed...Part timeFreelanceRemote workFlexible hours- Welo Data is hiring Data Labeling Associates in New York City for Project Perseus. The role involves evaluating Arabic language AI outputs and ensuring AI safety, requiring professional proficiency in Arabic and experience in writing and AI safety. You’ll critique models...
- ...Professional is hiring an Applied AI Data Scientist to help shape the next... ...enterprise stakeholders to design, evaluate, and continuously improve the... ..., multi-step reasoning, agent patterns, evaluation science)... ...prototypes to test ideas, de-risk assumptions, and explore UX and...RiskFull timeRemote workWorldwide
$36.06 - $38.47 per hour
...role in supporting the legal, compliance, safety, and risk-management work that helps advance our... ...to ensure that risk is appropriately evaluated and managed or mitigated. They provide... ...contribution toward your future each year.Robust professional development opportunities,...RiskRemote workWork from homeFlexible hours2 days per week3 days per weekASPCA
New York, NY3 days ago$91.4k - $159.9k
Our construction risk engineering group helps protect property, profitability... ...project management, site safety and operational management... ...with Claims to manage and evaluate subcontractor default claims,... ...program. You will apply your robust construction management experience...RiskFor contractorsFor subcontractorLocal areaRemote workFlexible hours- ...enterprises who are building AI systems to power... ...semantic search, RAG, and agents. We believe that our... ...Technical Staff in the Safety for Agents team, you will... ...algorithms, and evaluation methods to ensure Safety... ...the generalizability and robustness of ML systems. Proficiency...Full timeWork at officeRemote workFlexible hours
- Cohere, a leading security-first enterprise AI company, is seeking a Member of Technical Staff in the Safety for Agents team to advance safer LLMs through data generation, post-training algorithms, and evaluation methods. You'll collaborate with cross-functional ML teams...Remote workFlexible hours
- ...Crisis24 is a global, AI-enhanced provider of travel risk management, mass communications... ...across the globe. Our agents are not just security professionals... ..., ensuring the safety of personnel, property, and... ...Test (PRT) Meet-and-Greet evaluation (dependent on client/location...RiskWork at office
GardaWorld
New York, NY1 day ago $320k - $400k
As a Research Scientist on our team, you will partner with... ...on our track record of AI-powered solutions (e.g.... ...Research tackles high-risk, high-reward problems... ...backbone for our autonomous agents.Trained Agents for... ...RL training loops, and evaluation infrastructure needed to...Risk$204.44k - $324.99k
...and configure Agentforce agents, topics, instructions,... ...templates and grounded AI experiences using... ...Implement agent testing, evaluation, observability, and guardrails... ..., hallucination risk, data access, human-in-... ...insurance, 401(k) plans, and a robust suite of personal well-...RiskH1bLocal area- ...engineering, and visualization.As AI Data Scientist Senior Associate within... ...powered by LLMs and multi-agent patterns. You will develop data... ...solutions through testing, evaluation, and monitoring. Your... ...advice, raises capital, manages risk and extends liquidity in markets...RiskWork experience placement
- ...Risk Operations SpecialistBinance is a leading global blockchain ecosystem behind the world's largest cryptocurrency exchange by trading... ...to assess the legitimacy of accounts and account holders, evaluate associated risks, and ensure appropriate restriction or dismissal...RiskContract workFlexible hoursWeekend work
binance
New York, NY2 days ago $90k - $100k
...regulations, company policies, safety standards, and legal... ...company goals. Oversee and evaluate studio performance, operational... ...business contribution. Establish robust communication structures to ensure... ...improvement. Compliance, Risk Management & Corporate...RiskFor contractorsLocal areaFlexible hoursPlaytech
Atlantic City, NJ4 days ago$240k - $260k
...Team + The RoleThe Pendo for Agents team builds Pendo's AI and agent product area, a... ...on scope, sequencing, and risk while surfacing engineering... ...promotes ownership, psychological safety, and continuous improvement... ..., with the ability to evaluate new tools critically and...RiskWork at officeRemote workFlexible hours3 days per week$93.75k - $133.2k
...Special Agent Position Overview: The position advertised has... ...crimes that threaten public safety. Your transition from a specialized... ...Qualifications and Evaluations GL-09 All applicants must have... ...vulnerabilities, considering risks, and choosing the best outcome...RiskPermanent employmentFull timeWork experience placementWork at officeLocal areaImmediate startClearanceJobs
New York, NY1 day ago$103.24k - $133.2k
...Special Agent POSITION OVERVIEW The position advertised has... ...crimes that threaten public safety. Your transition from a specialized... ...QUALIFICATIONS AND EVALUATIONS All applicants must have two... ...vulnerabilities, considering risks, and choosing the best outcome...RiskPermanent employmentFull timeWork experience placementWork at officeLocal areaImmediate startFederal Bureau of Investigation (FBI)
New York, NY3 days ago- ...Crisis24 is a global, AI-enhanced provider of travel risk management, mass communications... ...across the globe. Our agents are not just security professionals... ..., ensuring the safety of personnel, property, and... ...Test (PRT) & Meet-and-Greet evaluation Background Investigation...RiskWork at office
Crisis24
New York, NY1 day ago
Do you want to receive more vacancies?
Subscribe and receive similar vacancies to AI Safety Scientist: Agent Robustness & Risk Evaluation. Be the first to apply!
Related searches
- ai data scientist New York, NY
- ai scientist New York, NY
- registered agent New York, NY
- right of way agent New York, NY
- enrolled agent New York, NY
- state farm agent work from home New York, NY
- work from home chat agent New York, NY
- transfer agent New York, NY
- booking agent New York, NY
- operations agent New York, NY