{"id":1399810,"url":"https://alion.io/job/epsilon-health-research-engineer-data-quality-evals","title":"Research Engineer / Research Scientist, Data Quality & Evaluations","company":{"id":3787074,"name":"Epsilon Health","domain":"epsilon.health","url":"https://alion.io/company/epsilon-health-2","size_band":"51-200","is_staffing_agency":false,"employer_type":"direct","is_intermediary":false,"listed_via":null,"ats_vendor":"Ashby","truth_index":null},"role":"AI/ML","role_family":"AI/ML","seniority":null,"employment_type":"full_time","work_mode":"on_site","remote_scope":null,"remote_scope_basis":null,"remote_working_hours":null,"hiring_geo_confidence":"structured","locations":["San Francisco, United States"],"countries":["US"],"hiring_countries":[],"hiring_countries_total":0,"salary":null,"salary_estimate":{"min_usd":165000,"max_usd":366000,"period":"year","method":"role_country_seniority_unknown","sample_n":4425},"experience_years_min":null,"visa_sponsorship":false,"relocation_package":false,"has_equity":false,"technologies":[{"name":"Human-in-the-Loop","optional":false},{"name":"Machine Learning","optional":false},{"name":"Multimodal AI","optional":false},{"name":"Post-training","optional":false},{"name":"Python","optional":false},{"name":"Databricks","optional":true},{"name":"Hallucination","optional":true},{"name":"LLM","optional":true},{"name":"NLP","optional":true},{"name":"Spark","optional":true}],"status":"live","first_seen_at":"2026-08-31T19:07:49Z","employer_posted_date":"2026-08-31","last_verified_at":"2026-10-31T03:21:42Z","board_verified":true,"closed_at":null,"days_open":60,"trust":{"level":"ok","repost_count":null,"flags":[],"days_open":60},"description":"About Us\nEpsilon Health is transforming medical imaging and diagnostics by bringing frontier AI into clinical practice. We're tackling some of healthcare's most critical challenges, building technology that directly improves patient outcomes.\nThis year, we've served over 300,000 patients and now serve 3,000+ daily, working with some of the largest medical institutions in the U.S. By year-end, we're on track to interpret 1% of all daily U.S. X-rays.\nOur research team brings experience from DeepMind and Meta, powered by one of the industry's most comprehensive proprietary medical imaging datasets, continuously enriched by real-world clinical data. Together, we're building a future where frontier AI helps save millions of lives today, not tomorrow.\nRecently out of stealth, we're proudly backed by Jack Altman, Uncork Capital, Renegade Partners, and AlleyCorp, one of NYC's most active healthcare venture firms.\nAbout the Role\nWe're looking for an exceptional Research Engineer or Research Scientist to advance how we curate data and evaluate frontier AI models for medical imaging.\nYou'll own the systems and methodologies that determine the quality of our training data and how we measure model performance, building the foundation for reliable, clinically accurate AI.\nYou'll tackle fundamental challenges in data-centric machine learning, multimodal evaluation, and clinical reliability, from identifying subtle dataset errors to developing rigorous benchmarks for radiology report generation.\nUnlike traditional research labs, you'll work with continuously growing real-world clinical data and feedback from practicing radiologists, developing evaluation methods that connect offline research performance with real-world clinical outcomes.\nYou'll work across our research team, collaborating closely with scientists and engineers developing vision foundation models, VLMs, and post-training methods. This is a highly autonomous role with the opportunity to identify critical research bottlenecks and solve them end to end.\nWhat You'll Do\nBuild the foundation for better models. Develop scalable data filtering, curation, and quality pipelines that improve the reliability of training datasets across medical imaging modalities.\n\nAdvance data-centric AI research. Explore novel approaches to detecting label noise, image-report misalignment, duplicates, and other subtle dataset quality issues.\n\nRedefine how AI is evaluated. Design rigorous evaluation frameworks for radiology report generation, measuring clinical accuracy, completeness, hallucinations, and factual consistency.\n\nConnect AI evaluation with clinical expertise. Work with radiologists to translate clinical judgment and expert feedback into scalable data quality and evaluation signals.\n\nDevelop intelligent evaluation systems. Build model-based evaluators, automated grading methods, and human-in-the-loop workflows that improve how we measure model quality.\n\nOwn research infrastructure end to end. Develop benchmarks, evaluation pipelines, and continuous regression testing that help researchers iterate quickly and confidently.\n\nDrive research across the organization. Identify bottlenecks across data, training, and evaluation, developing tools and methodologies that accelerate the entire research team.\n\nContribute to the research community. Share technical insights, develop best practices, and contribute to publications or open-source research.\n\nWhat We're Looking For\nWe care more about what you've built and discovered than where you've worked or how many years you've spent doing it.\nStrong expertise in machine learning, data-centric AI, model evaluation, or research engineering.\n\nDemonstrated ability to design and build robust data pipelines, evaluation systems, or ML research infrastructure.\n\nStrong Python programming skills and the ability to develop reliable, scalable research tooling.\n\nExperience in at least one of our core areas: dataset curation and quality, or evaluation of generative and multimodal models.\n\nAbility to independently identify research bottlenecks, formulate solutions, and execute projects end to end.\n\nStrong engineering fundamentals and experience working with complex datasets or machine learning systems.\n\nA rigorous, experimental mindset and the ambition to solve difficult, unsolved problems.\n\nNice to Have\nExperience developing evaluation frameworks for LLMs, VLMs, or other generative models.\n\nFamiliarity with data filtering, deduplication, label-noise detection, or active learning.\n\nExperience building model-based evaluators, LLM-as-judge systems, or human-in-the-loop annotation workflows.\n\nKnowledge of clinical evaluation methodologies, including factuality assessment, hallucination detection, or RadGraph-style metrics.\n\nBackground in medical imaging, radiology, clinical NLP, or other healthcare AI applications.\n\nExperience working with large-scale data processing tools such as Spark, Airflow, or Databricks.\n\nPublications or open-source contributions in machine learning, data-centric AI, evaluation, or medical AI.\n\nWe welcome exceptional researchers and engineers from both academic and industry backgrounds. A traditional career path or prior healthcare experience is not required.","description_format":"text","description_chars":5229,"description_truncated":false,"requirements":{"experience_years_min":null,"management_years_min":null,"team_size_min":null,"manages_managers":false,"education":null,"security_clearance":false,"languages":[]},"benefits":[],"hiring_locations":[],"hiring_excludes":[],"relocation_offered":false,"industries":["Medical AI","Radiology & Imaging Centers"],"lifecycle":[{"event":"open","at":"2026-09-28T14:50:57Z"}],"visa":[],"liveness":{"score":19,"band":"cold","label":"Long shot","p_open":1,"p_active":0.42,"p_room":0.45,"age_days":59,"expected_fill_days":30,"reasons":["conf:0","win:tail"],"computed_at":"2026-10-30T05:48:23Z"},"pay":null,"html_url":"https://alion.io/job/epsilon-health-research-engineer-data-quality-evals","json_url":"https://alion.io/job/epsilon-health-research-engineer-data-quality-evals.json","meta":{"generated_at":"2026-10-31T03:57:04Z","cache_seconds":300,"methodology":"https://alion.io/methodology","terms":"https://alion.io/terms","contact":"https://alion.io/contact","api":"https://alion.io/developers","about":"Alion is a live layer of people, companies and AI agents: who they are, whether they are real and active right now, what they do and how to work with them, readable by people and by agents and paid per call.","catalog":"https://alion.io/catalog.json","usage":{"tier":"crawler_verified","counted_by":"address","units_charged":1,"used_today":5593,"day_limit":null,"remaining_today":null,"minute_limit":300,"resets_at":"2026-11-01T00:00:00Z"}},"offers":[{"id":"company.slices","title":"One company in depth, by slice","status":"live","price":{"credits":0.02,"usd":0.002,"plus_per_slice":{"credits":0.05,"usd":0.005}},"unit":"per company, plus each slice with data","note":"the employer in depth","call":{"mcp_tool":"get_company","arguments":{"id":3787074},"rest":"https://alion.io/mcp/rest/get_company?id=3787074"},"human":"https://alion.io/catalog?offer=company.slices&for=job%2Fepsilon-health-research-engineer-data-quality-evals"},{"id":"market.stats","title":"A market slice: pay, demand and time to fill","status":"live","price":{"credits":1,"usd":0.1},"unit":"per slice","note":"pay, demand and time to fill for this role and place","call":{"mcp_tool":"market_stats"},"human":"https://alion.io/catalog?offer=market.stats&for=job%2Fepsilon-health-research-engineer-data-quality-evals"},{"id":"job.search","title":"Open jobs by role, technology, place, pay and visa","status":"live","price":{"credits":0.02,"usd":0.002},"unit":"per posting in a list","note":"similar open postings","call":{"mcp_tool":"search_jobs"},"human":"https://alion.io/catalog?offer=job.search&for=job%2Fepsilon-health-research-engineer-data-quality-evals"},{"id":"company.verify","title":"Is this company real and active right now","status":"pilot","price":null,"unit":"per company","request":{"url":"https://alion.io/catalog/request","method":"POST","body":"{\"offer\": \"company.verify\", \"for\": \"job/epsilon-health-research-engineer-data-quality-evals\", \"note\": \"what you need it for\"}"},"human":"https://alion.io/catalog?offer=company.verify&for=job%2Fepsilon-health-research-engineer-data-quality-evals"}],"agent":{"mcp":"https://alion.io/mcp/jobs","mcp_open":"https://alion.io/mcp/open","next":[{"tool":"get_job","arguments":{"id":1399810}},{"tool":"search_jobs","arguments":{"company":"epsilon.health","detail":"compact"}},{"tool":"match_people","arguments":{"job_id":1399810},"note":"people open to offers who fit this vacancy"}],"note":"The same data through MCP tools: https://alion.io/mcp/open needs no sign-in (compact searches, postings, people); https://alion.io/mcp with an Alion account has everything. Docs: https://alion.io/developers"}}