{"schemaVersion":"jobsearcher.job.v1","id":"0cfdddfe410d95bb85bfb6cc","url":"https://jobsearcher.com/jobs/0cfdddfe410d95bb85bfb6cc","canonicalUrl":"https://jobsearcher.com/jobs/0cfdddfe410d95bb85bfb6cc","title":"Machine Learning Researcher - Post Training","description":"ML Researcher, Post-Training Infrastructure$240k - $320k base + significant equity (up to x%)New York - Hybrid/ RemoteMorpheus are partnered with a fast-growing healthcare AI company to help find their next ML Researcher, Post-Training Infrastructure.Our client is building the evaluation and training infrastructure for autonomous healthcare AI. They create high-fidelity training gyms that help frontier models improve on real clinical, operational, administrative, and research workflows, using RL environments, long-horizon evaluations, expert feedback, and real-world healthcare data. Instead of selling raw data, they help AI labs turn model failures into measurable performance gains on regulated, economically valuable healthcare tasks.They are already commercially live with six-figure ARR, have sourced tens of millions of longitudinal multimodal patient records, are actively in procurement with multiple frontier labs, and have a large and growing commercial pipeline. Models trained in their environments have generalized to a double-digit percentage improvement on a leading agentic medical benchmark. Autonomous AI is the frontier, and our client is building the critical infrastructure that unlocks it for healthcare.They are looking for exceptional ML Researchers to help deliver post-training datasets, evaluations, and RL environments to leading AI labs. This role is ideal for someone who wants to work at the frontier of applied ML, reinforcement learning, evaluation, and healthcare, and who is excited to build systems that meaningfully improve model performance in one of the highest-stakes domains in the world.What you'll doDesign and build high-fidelity post-training environments for healthcare workflows, including clinical reasoning, revenue cycle, administrative operations, care management, and biomedical research.Translate real-world healthcare workflows into rigorous model training and evaluation tasks.Analyze model failures and convert them into targeted datasets, reward functions, evals, and RL environments.Work directly on deliverables for frontier AI labs, including benchmarks, rollouts, environment specs, expert feedback loops, and post-training data pipelines.Collaborate with clinicians, domain experts, and engineers to define what \"good\" model performance looks like in complex healthcare settings.Help build infrastructure for long-horizon agent evaluation, reward modeling, trajectory generation, and model improvement.Move quickly from ambiguous research questions to concrete artifacts that improve frontier model performance.What they're looking forStrong ML research or engineering background, ideally with experience in one or more of:Reinforcement learningPost-training / SFT / preference data / RLHF / RLAIFEvaluation and benchmarkingAgentic systemsSynthetic data generationReward modelingLLM fine-tuning or model behavior analysisAbility to reason from first principles about model failures, task design, and evaluation quality.Strong coding ability and comfort building research infrastructure quickly.High agency, strong ownership, and ability to operate in a fast-moving startup environment.Strong written communication. You should be able to clearly document tasks, environments, rubrics, model failures, and experimental results.Interest in healthcare, biology, medicine, or life sciences.Nice to haveClinical, medical, biology, or biomedical research background.Experience working with healthcare data, EHRs, claims, clinical workflows, or biomedical datasets.Prior experience building evals, agents, RL environments, or post-training datasets for frontier models.Experience working with human expert feedback, annotation systems, or quality-control pipelines.Publications, open-source work, or strong project work in ML, RL, LLMs, agents, or healthcare AI.Why joinThis is a chance to work on one of the most important bottlenecks in AI: making autonomous agents reliable in real-world, high-stakes domains. Healthcare will not be solved by generic models alone. It requires domain-specific evaluations, training environments, reward signals, and feedback loops grounded in real workflows. Our client is building that infrastructure.You will work directly on post-training systems for leading AI labs, with access to real-world healthcare data, expert clinical feedback, and commercially urgent customer demand. Our client is a small team, actively fundraising, in diligence with multiple funds, and hiring to meet immediate lab delivery needs. This is an opportunity to join at the ground floor of a company positioned to become the healthcare-specific post-training layer for autonomous AI.","company":"Morpheus Talent Solutions","rawCompany":"morpheus talent solutions","city":"Ny","state":"WAL","isRemote":false,"isActive":false,"createdAt":"2026-07-14T07:38:36.004Z","occupations":[{"code":"15-1221.00","title":"Computer and Information Research Scientists","slug":"computer-and-information-research-scientists"},{"code":"15-2051.00","title":"Data Scientists","slug":"data-scientists"},{"code":"15-1252.00","title":"Software Developers","slug":"software-developers"}],"industries":[{"code":"541512","title":"Computer Systems Design Services","slug":"computer-systems-design-services"},{"code":"541990","title":"All Other Professional, Scientific, and Technical Services","slug":"all-other-professional-scientific-and-technical-services"},{"code":"541690","title":"Other Scientific and Technical Consulting Services","slug":"other-scientific-and-technical-consulting-services"}],"jobPosting":{"@context":"https://schema.org","@type":"JobPosting","title":"Machine Learning Researcher - Post Training","description":"ML Researcher, Post-Training Infrastructure$240k - $320k base + significant equity (up to x%)New York - Hybrid/ RemoteMorpheus are partnered with a fast-growing healthcare AI company to help find their next ML Researcher, Post-Training Infrastructure.Our client is building the evaluation and training infrastructure for autonomous healthcare AI. They create high-fidelity training gyms that help frontier models improve on real clinical, operational, administrative, and research workflows, using RL environments, long-horizon evaluations, expert feedback, and real-world healthcare data. Instead of selling raw data, they help AI labs turn model failures into measurable performance gains on regulated, economically valuable healthcare tasks.They are already commercially live with six-figure ARR, have sourced tens of millions of longitudinal multimodal patient records, are actively in procurement with multiple frontier labs, and have a large and growing commercial pipeline. Models trained in their environments have generalized to a double-digit percentage improvement on a leading agentic medical benchmark. Autonomous AI is the frontier, and our client is building the critical infrastructure that unlocks it for healthcare.They are looking for exceptional ML Researchers to help deliver post-training datasets, evaluations, and RL environments to leading AI labs. This role is ideal for someone who wants to work at the frontier of applied ML, reinforcement learning, evaluation, and healthcare, and who is excited to build systems that meaningfully improve model performance in one of the highest-stakes domains in the world.What you'll doDesign and build high-fidelity post-training environments for healthcare workflows, including clinical reasoning, revenue cycle, administrative operations, care management, and biomedical research.Translate real-world healthcare workflows into rigorous model training and evaluation tasks.Analyze model failures and convert them into targeted datasets, reward functions, evals, and RL environments.Work directly on deliverables for frontier AI labs, including benchmarks, rollouts, environment specs, expert feedback loops, and post-training data pipelines.Collaborate with clinicians, domain experts, and engineers to define what \"good\" model performance looks like in complex healthcare settings.Help build infrastructure for long-horizon agent evaluation, reward modeling, trajectory generation, and model improvement.Move quickly from ambiguous research questions to concrete artifacts that improve frontier model performance.What they're looking forStrong ML research or engineering background, ideally with experience in one or more of:Reinforcement learningPost-training / SFT / preference data / RLHF / RLAIFEvaluation and benchmarkingAgentic systemsSynthetic data generationReward modelingLLM fine-tuning or model behavior analysisAbility to reason from first principles about model failures, task design, and evaluation quality.Strong coding ability and comfort building research infrastructure quickly.High agency, strong ownership, and ability to operate in a fast-moving startup environment.Strong written communication. You should be able to clearly document tasks, environments, rubrics, model failures, and experimental results.Interest in healthcare, biology, medicine, or life sciences.Nice to haveClinical, medical, biology, or biomedical research background.Experience working with healthcare data, EHRs, claims, clinical workflows, or biomedical datasets.Prior experience building evals, agents, RL environments, or post-training datasets for frontier models.Experience working with human expert feedback, annotation systems, or quality-control pipelines.Publications, open-source work, or strong project work in ML, RL, LLMs, agents, or healthcare AI.Why joinThis is a chance to work on one of the most important bottlenecks in AI: making autonomous agents reliable in real-world, high-stakes domains. Healthcare will not be solved by generic models alone. It requires domain-specific evaluations, training environments, reward signals, and feedback loops grounded in real workflows. Our client is building that infrastructure.You will work directly on post-training systems for leading AI labs, with access to real-world healthcare data, expert clinical feedback, and commercially urgent customer demand. Our client is a small team, actively fundraising, in diligence with multiple funds, and hiring to meet immediate lab delivery needs. This is an opportunity to join at the ground floor of a company positioned to become the healthcare-specific post-training layer for autonomous AI.","datePosted":"2026-07-14T07:38:36.004Z","dateModified":"2026-07-14T07:38:36.004Z","hiringOrganization":{"@type":"Organization","name":"Morpheus Talent Solutions","sameAs":"https://jobsearcher.com"},"jobLocation":{"@type":"Place","address":{"@type":"PostalAddress","addressLocality":"Ny","addressRegion":"WAL","addressCountry":"US"}},"identifier":{"@type":"PropertyValue","name":"JobSearcher","value":"0cfdddfe410d95bb85bfb6cc"},"url":"https://jobsearcher.com/jobs/0cfdddfe410d95bb85bfb6cc"}}