Apply

Ready to go for it?

AI Apply speeds things up—apply directly if you prefer.

FREE ACCESS
5,000–10,000 jobs/day
Scoutfield Logo

See all jobs on Scoutfield

Search thousands of fresh jobs every day.

Discover
  • Fresh listings
  • Fast filters
  • No subscription required
Create a free account and start exploring right away.
Abridge

Member of Technical Staff, Generative AI

Abridge

. Design and build agentic systems that turn LLMs into composable, dependable tools .

Posted 10/2/2026full-timeUnited StatesLead💰 $255,000 - $300,000 per yearWebsite

Core Competencies

Role fit
Core Competencies

Use this summary to align your resume positioning with the role.

Demonstrates expertise in building and optimizing LLM-powered systems, with a strong focus on modular code development, model evaluation, and collaboration with cross-functional teams. Proficient in managing workflows, conducting experiments, and implementing monitoring systems to ensure high-quality, dependable outputs.

Highest-signal resume keywords
LLM API ProficiencyPython ProgrammingModel Evaluation ExperienceA/B Testing ExperienceAgentic Workflow Management

ATS Keywords

Tailor your resume
Applicant Tracking System Keywords

Tip: use these terms in your resume and cover letter to boost ATS matches.

Hard Skills
Production-Grade Systems DevelopmentModular Code WritingData Set BuildingAutomated Evaluation FrameworksAsync ProgrammingPerformance ProfilingTool UsePrompting StrategiesOrchestration PatternsContext Management
Soft Skills
CollaborationProblem-SolvingAdaptability
Tools & Technologies
LangChainLlamaIndexVector DatabasesRetrieval SystemsMonitoring Systems
Industry Keywords
Agentic SystemsLLM-Powered ProductsHuman-In-The-Loop EvaluationClinical SystemsLow-Latency Environments

Tech Stack

Tools & technologies
Python

About the role

Key responsibilities & impact
  • Design and build agentic systems that turn LLMs into composable, dependable tools
  • Leverage retrieval, tool use, agentic reasoning, and structured outputs
  • Collaborate with ML and infrastructure engineers to scale and optimize agentic workflows
  • Manage latency, context windows, and model choice
  • Write high-quality, modular code that is graceful under failure and easy to iterate on
  • Own major architectural decisions involving workflows, data flow, intermediate-state caching, and generative-output structure
  • Build benchmark datasets and automated and human-in-the-loop evaluation frameworks
  • Design experiments to surface failure modes and edge cases
  • Run A/B tests and distill clinician feedback into actionable model-improvement insights
  • Rapidly prototype with new models, model capabilities, open-source tools, and prompting techniques
  • Productionize LLM workflows by deploying models into low-latency, high-uptime environments
  • Build monitoring and observability systems
  • Implement post-processing guardrails
  • Manage workflow versioning
  • Collaborate with researchers, clinicians, engineers, ML engineers, and infrastructure engineers to translate language-model capabilities into dependable clinical systems

Requirements

What you’ll need
  • 3+ years of experience building production-grade systems
  • 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, including semantic and lexical retrieval, vector databases, efficient kNN, function calling, tool use, or agentic workflows
  • Working knowledge of model evaluation
  • Experience building diverse datasets
  • Experience conducting automated and human-in-the-loop evaluations
  • Experience running A/B tests
  • Experience working with subject matter experts to guide model improvement
  • Strong Python fundamentals
  • Ability to write clean code and design comprehensive test cases
  • Familiarity with core Python language features and standard libraries
  • Willingness to work from the San Francisco or New York City office at least 3 times per week
  • Must be willing to work under a hybrid model
  • Candidates must be currently based in the United States or be authorized to work in the United States
  • Experience with async programming, performance profiling, packaging, and deployment tooling is strongly preferred

Benefits

Comp & perks
  • 14 paid holidays
  • Flexible PTO for salaried employees
  • Accrued time off for hourly employees
  • Medical, Dental, and Vision coverage for all full-time employees and their families
  • Monthly HSA contributions for eligible High Deductible Health Plan participants
  • Paid parental leave for all full-time employees
  • Family forming benefits and financial support
  • 401(k) matching
  • Personal device allowance
  • Flexible Spending Accounts (FSA)
  • Commuter Benefits
  • Lifestyle Wallet contributions for fitness, professional development, coworking, and more
  • Mental health therapy and coaching support
  • Paid sabbatical leave after 5 years of employment
  • Competitive compensation and equity grants for full-time employees
  • Relocation assistance for candidates willing to move to San Francisco
  • Flexible work hours
  • Inclusive culture
  • Ongoing learning opportunities