As a Member of Technical Staff, Multimodal Safety, you will work to develop and implement cutting-edge safety methodologies for post-training multimodal large language models to be served to millions of users through Copilot every day.
\nWe work on the bleeding edge and leverage the most powerful pretrained models and algorithms, making it critical that we ensure our AI systems behave safely and align with organisational values.
\nYou will be responsible for designing novel safety evaluation frameworks, curating high-quality data for robust evaluations and training, prototyping new safety capabilities, and developing safety-focused fine-tuning algorithms.
\nWe're looking for outstanding individuals with deep expertise in multimodal AI safety who can translate research insights into practical solutions while being a strong communicator and collaborative teammate.
\nThe ideal candidate takes the initiative in exploring new safety methodologies and enjoys building world-class, trustworthy AI experiences in a fast-paced applied research environment.
\nMicrosoft's mission is to empower every person and every organisation on the planet to achieve more.
\nAs employees we come together with a growth mindset, innovate to empower others, and collaborate to realise our shared goals.
\nEach day we build on our values of respect, integrity, and accountability to create a culture of inclusion where everyone can thrive at work and beyond.
\nResponsibilities:
\nLeverage expertise in multimodal safety to uncover potential risks and develop novel mitigation strategies, including alignment techniques and robustness improvements for multimodal large language models.
\nCreate and implement comprehensive evaluation frameworks and red-teaming methodologies to assess model safety across diverse scenarios, edge cases, and potential failure modes.
\nBuild automated safety testing systems, generalise safety solutions into repeatable frameworks, and write efficient code for safety pipelines and intervention systems.
\nMaintain a user-oriented perspective by understanding safety needs from user perspectives, validating safety approaches through user research, and serving as a trusted advisor on multimodal safety matters.
\nTrack advances in multimodal safety research, identify relevant state-of-the-art techniques, and adapt safety algorithms to drive innovation in production systems serving millions of users.
\nEmbody our culture and values.
\nXML job scraping automation by YubHub
","url":"https://yubhub.co/jobs/job_930f14dd-03d","directApply":true,"hiringOrganization":{"@type":"Organization","name":"Microsoft","sameAs":"https://microsoft.ai","logo":"https://logos.yubhub.co/microsoft.ai.png"},"x-apply-url":"https://microsoft.ai/job/member-of-technical-staff-multimodal-safety-mai-super-intelligence-team-3/","x-work-arrangement":"hybrid","x-experience-level":"staff","x-job-type":"full-time","x-salary-range":"$119,800 - $234,700 per year","x-skills-required":["multimodal safety","diffusion models","image generation","video generation","audio generation","safety evaluation frameworks","red-teaming methodologies","automated safety testing systems","safety pipelines","intervention systems"],"x-skills-preferred":["multimodal LLM safety","evaluation frameworks","automated red-teaming","guardrail systems","safety pipelines","user-validated safety decisions"],"datePosted":"2026-03-08T22:19:30.911Z","jobLocation":{"@type":"Place","address":{"@type":"PostalAddress","addressLocality":"New York"}},"employmentType":"FULL_TIME","occupationalCategory":"Engineering","industry":"Technology","skills":"multimodal safety, diffusion models, image generation, video generation, audio generation, safety evaluation frameworks, red-teaming methodologies, automated safety testing systems, safety pipelines, intervention systems, multimodal LLM safety, evaluation frameworks, automated red-teaming, guardrail systems, safety pipelines, user-validated safety decisions","baseSalary":{"@type":"MonetaryAmount","currency":"USD","value":{"@type":"QuantitativeValue","minValue":119800,"maxValue":234700,"unitText":"YEAR"}}}]}