{"schemaVersion":"jobsearcher.job.v1","id":"b8b1757a35288ed9c816cd21","url":"https://jobsearcher.com/jobs/b8b1757a35288ed9c816cd21","canonicalUrl":"https://jobsearcher.com/jobs/b8b1757a35288ed9c816cd21","title":"Research Engineer","description":"Lead AI Research Engineer – Agentic SystemsNew York (hybrid)Our client, a global information and technology company, is hiring a Lead AI Research Engineer for its applied AI research group. The team builds AI products used by professionals in law, tax, compliance and government around the world. These are high-stakes domains where accuracy and trust matter.The roleYou’ll lead the technical design and delivery of production agentic AI systems, taking each one from an unclear business problem to a system customers can rely on. You’ll set engineering standards, mentor other engineers and work closely with research scientists to turn new ideas into products.What you’ll doDesign, build and optimise multi-agent systems for production, including complex tool calling, context management and workflow orchestrationBuild evaluation frameworks that go beyond offline metrics to measure how agents actually perform in live systemsOwn agent observability and telemetryLead engagement across Product, UX, Engineering and Business stakeholdersSet best practices and standards that scale, and raise the technical bar through mentorshipBuild scalable data pipelines and ML systems across the full software lifecycleWhat you’ll bring8+ years of hands-on engineering experience building IR, NLP, LLM or agentic systems for commercial products in production (not academic or experimental work)Deep expertise in agentic AI: tool use, multi-agent orchestration, context management and agent evaluationExpert-level production Python: clean, tested, maintainable code. Pydantic/PydanticAI experience is a strong plusFamiliarity with PyTorch and Hugging Face, and a solid grasp of ML fundamentalsExperience with LLM observability/eval platforms such as Langfuse or BraintrustCloud-native and MLOps experience (AWS or Azure)A track record of leading technical workstreams and influencing cross-functional stakeholdersDaily use of AI-assisted coding tools such as Cursor or Claude CodeNice to have: NER, information extraction or retrieval experience; Java/TypeScriptWhat’s on offerCompetitive salary and benefitsHybrid working, plus up to 8 weeks a year working from anywhereFlexible vacation, wellbeing support and tuition reimbursementWork on AI products used by millions of professionals worldwide","company":"Primis","rawCompany":"primis","city":"None","isRemote":false,"isActive":true,"createdAt":"2026-10-17T01:59:44.966Z","occupations":[{"code":"15-1221.00","title":"Computer and Information Research Scientists","slug":"computer-and-information-research-scientists"},{"code":"15-1252.00","title":"Software Developers","slug":"software-developers"},{"code":"17-2199.00","title":"Engineers, All Other","slug":"engineers-all-other"}],"industries":[{"code":"541990","title":"All Other Professional, Scientific, and Technical Services","slug":"all-other-professional-scientific-and-technical-services"},{"code":"513210","title":"Software Publishers","slug":"software-publishers"},{"code":"541511","title":"Custom Computer Programming Services","slug":"custom-computer-programming-services"}],"jobPosting":{"@context":"https://schema.org","@type":"JobPosting","title":"Research Engineer","description":"Lead AI Research Engineer – Agentic SystemsNew York (hybrid)Our client, a global information and technology company, is hiring a Lead AI Research Engineer for its applied AI research group. The team builds AI products used by professionals in law, tax, compliance and government around the world. These are high-stakes domains where accuracy and trust matter.The roleYou’ll lead the technical design and delivery of production agentic AI systems, taking each one from an unclear business problem to a system customers can rely on. You’ll set engineering standards, mentor other engineers and work closely with research scientists to turn new ideas into products.What you’ll doDesign, build and optimise multi-agent systems for production, including complex tool calling, context management and workflow orchestrationBuild evaluation frameworks that go beyond offline metrics to measure how agents actually perform in live systemsOwn agent observability and telemetryLead engagement across Product, UX, Engineering and Business stakeholdersSet best practices and standards that scale, and raise the technical bar through mentorshipBuild scalable data pipelines and ML systems across the full software lifecycleWhat you’ll bring8+ years of hands-on engineering experience building IR, NLP, LLM or agentic systems for commercial products in production (not academic or experimental work)Deep expertise in agentic AI: tool use, multi-agent orchestration, context management and agent evaluationExpert-level production Python: clean, tested, maintainable code. Pydantic/PydanticAI experience is a strong plusFamiliarity with PyTorch and Hugging Face, and a solid grasp of ML fundamentalsExperience with LLM observability/eval platforms such as Langfuse or BraintrustCloud-native and MLOps experience (AWS or Azure)A track record of leading technical workstreams and influencing cross-functional stakeholdersDaily use of AI-assisted coding tools such as Cursor or Claude CodeNice to have: NER, information extraction or retrieval experience; Java/TypeScriptWhat’s on offerCompetitive salary and benefitsHybrid working, plus up to 8 weeks a year working from anywhereFlexible vacation, wellbeing support and tuition reimbursementWork on AI products used by millions of professionals worldwide","datePosted":"2026-10-17T01:59:44.966Z","dateModified":"2026-10-17T01:59:44.966Z","hiringOrganization":{"@type":"Organization","name":"Primis","sameAs":"https://jobsearcher.com"},"jobLocation":{"@type":"Place","address":{"@type":"PostalAddress","addressLocality":"None","addressCountry":"US"}},"identifier":{"@type":"PropertyValue","name":"JobSearcher","value":"b8b1757a35288ed9c816cd21"},"url":"https://jobsearcher.com/jobs/b8b1757a35288ed9c816cd21"}}