The RoleWe're seeking an experienced AI/ML engineer who is motivated to meaningfully improve the way healthcare is administered in the United States. You'll be responsible for making the core Onos Health AI extraction and evaluation systems accurate, consistent, and trustworthy enough for health plans to depend on. As an early team member, you'll be expected to wear multiple hats and ensure excellent outcomes for our enterprise customers. This role is a hybrid role based in San Francisco, where you'll be expected to work at our office in person 2-3 times a week.
What you'll be doing at Onos:- Develop LLM/NLU systems to process and extract meaningful information from clinical notes and medical documents, classify patients according to level-of-care guidelines, and make accurate recommendations
- Own and evolve our LLM evaluation harness, regression gates, and observability to ensure our systems catch accuracy regressions before they reach payers and prove the platform's reliability over time
- Extract structured data from visually complex clinical documents, including scanned charts, tables, and graphs using a mix of OCR, multimodal models, and classical ML
- Collaborate with backend engineers to integrate AI/ML capabilities seamlessly into the Onos platform
Technical Challenges At Onos:- Build and operationalize AI/data pipelines to analyze medical records to streamline clinical assessments and healthcare quality reviews
- Benchmark and stress-test LLM systems so evidence extraction and level-of-care classification stay accurate and reliable as criteria, documents, and models change
- Develop and optimize a system that ingests complex medical standards of care documents and evaluates provider adherence to guidelines
- Design explainable AI solutions that provide transparency into model decisions for healthcare professionals
Tech Stack:- Infrastructure/Systems: AWS (ECS, Bedrock, Cognito, etc.), Docker, Github Actions
- Languages/Frameworks: Python, Django, Celery, django-ninja, django-tenants
- Database/Storage: PostgreSQL (AWS RDS), S3
- Development Tools: Github, Jira, CoderabbitAI, Tusk, Claude
What we're looking for:- 4+ years experience building and deploying applications in production in a backend engineering / data engineering capacity
- Relevant experience with developing LLM-based systems for ingesting and evaluating unstructured records for industry-specific use cases and integrating them with user-facing features
- Experience with document AI, OCR, or extracting data from visual/scanned content (charts, graphs, tables)
- Deep understanding of the limitations of using LLMs and the best practices for using them for reliable, consistent, and accurate outputs
- Customer obsessed and motivated to build best-in-class models for behavioral health clinical assessments in the healthcare space
- A collaborative team player with a focus on delivering measurable results
Bonus points if you have:- Specifically worked with medical records to evaluate whether a patient's history meets criteria for evaluations or assessments (e.g., claims authorization or other types of evaluations)
- Experience wearing multiple hats as a generalist backend engineer
- Experience working with data pipelines and Python and related data science/ML libraries
- Significant experience working with healthcare data and with HIPAA best practices
- Knowledge of modern LLM and ML infrastructure and MLOps best practices
Benefits and Perks- Flexible hybrid arrangement: 2-3 days/week at San Francisco office (Financial District), remote-first culture
- Unlimited vacation policy
- Paid parental leave
- Medical, dental, and vision insurance
- Pre-tax commuter benefits
- 401(k)
- Significant equity as an early employee
- Direct mentorship from experienced founders
- Ground-floor opportunity to help build a team and culture
- Regular team events and offsites
- Company-provided equipment and home office setup
