Skip to content
AbridgeAbridgeSan Francisco, CA

Software Engineer

Early-career Software Engineer building and iterating on agentic LLM systems, RAG pipelines, evaluation frameworks, and backend/frontend components for AI-powered clinical documentation at Abridge. Requires CS degree or equivalent plus hands-on GenAI experience from projects, internships or coursework.

157k – 184k
On-siteEntry levelML Engineering

About the role

What You'll Do

  • Build and iterate on agentic LLM systems — including retrieval pipelines, structured tool use, and chained LLM workflows — as part of a collaborative engineering team
  • Contribute to evaluation frameworks that measure accuracy, robustness, and clinical reliability — including automated pipelines and human-in-the-loop review
  • Contribute to backend and frontend systems across Abridge
  • Think with an agent-first approach. Continuously learn and relearn agentic coding.
  • Fine-tune your judgment on where the human in the loop is critical.
  • Help prototype with new models, prompting techniques, and open-source orchestration tools (LangChain, LlamaIndex, etc.)
  • Contribute to monitoring and observability systems that keep our LLM workflows healthy in production
  • Collaborate across ML, infrastructure, product, and clinical teams — and develop a genuine understanding of the users and clinicians we serve
  • Learn from senior engineers and bring curiosity and fresh perspective to every problem

What You'll Bring

  • A degree in CS or a related field, or equivalent experience (projects, bootcamp, open source — we care about what you can build not where you learned it)
  • Hands-on GenAI experience — through coursework, personal projects, internships, or hackathons. You've integrated an LLM API, built a RAG pipeline, experimented with agents, or shipped something AI-powered and can speak to what you learned
  • Familiarity with LLM orchestration concepts (prompt chaining, tool use, retrieval) even if you haven't yet used them in a production setting
  • AI tooling is already part of how you work — you use it to write, debug, and learn faster, and you know when to trust it vs. verify
  • Curiosity about model evaluation, failure modes, and what it actually takes to make an LLM system reliable
  • Collaborative, low-ego mindset — we move fast, and we need teammates who pitch in wherever needed

Compensation and Benefits

  • Competitive compensation and equity grants for full time employees
  • Generous Time Off: 14 paid holidays, flexible PTO for salaried employees
  • Comprehensive Health Plans: Medical, Dental, and Vision coverage
  • Generous HSA Contribution
  • Paid Parental Leave
  • Family Forming Benefits
  • 401(k) Matching
  • Personal Device Allowance
  • Pre-tax Benefits: FSA and Commuter Benefits
  • Lifestyle Wallet: Monthly contributions for fitness, professional development, coworking, and more
  • Mental Health Support: therapy and coaching
  • Sabbatical Leave after 5 years

Skills

LLMsRAGLangChainLlamaindexPythonJavaScriptAgentic SystemsPrompt EngineeringEvaluation FrameworksRetrieval Pipelines

Similar roles

ML Engineering jobs
Baseten

Software Engineer, Model Performance Tooling

BasetenSan Francisco, CA

Builds performance benchmarking, diagnostic, and optimization tools for LLM inference on GPU clusters. Early-career role requiring Python proficiency, systems curiosity, and interest in AI hardware—no prior experience needed.

160k – 200k
On-siteEntry levelML Engineering
Nuro

Software Engineer, ML Infrastructure, Optimization

NuroMountain View, CA

Build and optimize ML infrastructure for autonomous vehicles, focusing on model optimization, compilers, and deployment across the autonomy stack. Requires 2+ years in ML optimization and strong Python/C++/CUDA skills.

160k – 241k
On-site2+ YOEML Engineering
Nuro

Software Engineer, Performance

NuroMountain View, CA

New grad software engineer optimizing performance of autonomous vehicle software. Profile, debug, and reduce latency of C++ systems running on x86, ARM, and GPUs while building tools for memory management and high-performance code.

153k – 175k
On-siteEntry levelML Engineering
Turquoise Health

Software Engineer II, AI

Turquoise HealthChicago, IL

Software Engineer building and shipping AI-enabled features and workflows for a healthcare price transparency platform. Requires 2+ years Python experience and SQL knowledge.

153k – 170k
Remote2+ YOEML Engineering
Harvey

Software Engineer, Agents

HarveySan Francisco, CA +1

Builds AI agents for legal workflows, optimizing performance via prompt engineering, model selection, tools, and evaluations. Partners with PMs and customers to ship low-latency, high-quality agent systems using Python and LLM APIs. Requires 2-5 years experience.

161k – 242k
Hybrid2+ YOEML Engineering