Base Salary
$255k - $300k/yr
Responsibilities
- Design and build agentic LLM systems using retrieval, tool use, agentic reasoning, and structured outputs.
- Collaborate with ML and infrastructure engineers to scale and optimize workflows, latency, context windows, and model selection.
- Write modular, failure-tolerant, maintainable code and make major architectural decisions regarding data flow, caching, and generative outputs.
- Build benchmark datasets and automated and human-in-the-loop evaluation frameworks.
- Design experiments, simulate edge cases, run A/B tests, analyze clinician feedback, and identify failure modes.
- Prototype new models, model capabilities, open-source tools, and prompting techniques.
- Productionize LLM workflows by deploying them to low-latency, high-uptime environments and building monitoring, observability, guardrails, and versioning systems.
Requirements
- 3+ years of experience building production-grade systems, including 1–2+ years focused on LLM-powered or agentic products.
- Deep fluency with LLM APIs, prompting strategies, and orchestration patterns such as LangChain, LlamaIndex, or custom pipelines.
- Experience with retrieval systems, vector databases, efficient k-nearest-neighbor retrieval, function calling, tool use, or agentic workflows.
- Working knowledge of model evaluation, diverse dataset development, automated and human-in-the-loop evaluation, A/B testing, and subject-matter-expert collaboration.
- Strong Python fundamentals, including clean code, comprehensive test cases, core language features, and standard libraries.
- Experience with asynchronous programming, performance profiling, packaging, and deployment tooling is strongly preferred.
- Must be willing to work from the San Francisco or New York office at least three times per week.
Benefits
- Hybrid work model with at least three office days per week in San Francisco or New York; relocation assistance is available for candidates moving to San Francisco.
- 14 paid holidays, flexible PTO for salaried employees, and accrued time off for hourly employees.
- Medical, dental, and vision coverage for full-time employees and their families, plus HSA contributions for eligible high-deductible plans.
- Paid parental leave and family-forming resources and financial support.
- 401(k) matching, pre-tax FSA and commuter benefits, and a tax-free personal device allowance.
- Monthly lifestyle wallet contributions for fitness, professional development, coworking, and more.
- Mental health therapy and coaching support.
- Paid sabbatical leave after five years of employment.
- Competitive compensation and equity grants for full-time employees.
Tech Stack
Categories
About Abridge
Founded in 2018, Abridge is the first AI-native clinician intelligence platform organized around the patient, built for clinicians, and designed to help health systems coordinate the clinical, financial, and evidence-based decisions for every moment of care. Powered by purpose-built AI for healthcare, Abridge connects patients, providers, payers, and life sciences companies. This year, the platform will support more than 100 million patient-clinician conversations across 300 of the largest and most complex health systems in the U.S. With deep EHR integration, Abridge’s automatic speech recognition and note generation has been validated to capture encounters in 28+ languages across specialties and care settings. Abridge is setting the industry standard for the responsible deployment of AI across health systems. Features like Linked Evidence map AI-generated clinical documentation to source data, helping clinicians quickly trust and verify the output. Abridge was awarded Best in KLAS for Ambient AI in 2025 and 2026, in addition to other accolades, including TIME Best Inventions of 2024 and 2025, CNBC Disruptor 2025, and Fast Company’s Most Innovative Companies 2025.