Abridge is seeking GenAI Software Engineers to join a cross-disciplinary team and translate cutting-edge language model capabilities into dependable clinical systems. You will design advanced LLM-driven workflows that reason through complex clinical contexts, leverage agentic capabilities and structured tool use, navigate branching chains of LLM calls, and integrate with retrieval systems to consistently generate outputs clinicians can trust. A major focus will be developing and applying rigorous evaluation frameworks (automated and human-in-the-loop) to assess accuracy, robustness, multilingual capabilities, and more. You will design experiments to probe failure modes, simulate edge cases, stress-test LLM workflows under realistic conditions, and employ a data-driven approach to understand model behavior, build benchmarking tools, run A/B tests, and translate clinician feedback into model improvements. The role owns end-to-end productionization of LLM workflows: deploying models into low-latency, high-uptime environments, building monitoring and observability, implementing post-processing guardrails, and managing workflow versioning. Responsibilities include designing and building agentic systems that turn LLMs into dependable tools with retrieval, tool use, agentic reasoning, and structured outputs; collaborating with ML and infra engineers to scale and optimize workflows; writing high-quality modular code; making major architectural decisions; driving rigorous evaluation; leveraging frontier capabilities to prototype with new models and open-source tools; and continuousl

Abridge is seeking GenAI Software Engineers to join a cross-disciplinary team and translate cutting-edge language model capabilities into dependable clinical systems. You will design advanced LLM-driven workflows that reason through complex clinical contexts, leverage agentic capabilities and structured tool use, navigate branching chains of LLM calls, and integrate with retrieval systems to consistently generate outputs clinicians can trust. A major focus will be developing and applying rigorous evaluation frameworks (automated and human-in-the-loop) to assess accuracy, robustness, multilingual capabilities, and more. You will design experiments to probe failure modes, simulate edge cases, stress-test LLM workflows under realistic conditions, and employ a data-driven approach to understand model behavior, build benchmarking tools, run A/B tests, and translate clinician feedback into model improvements. The role owns end-to-end productionization of LLM workflows: deploying models into low-latency, high-uptime environments, building monitoring and observability, implementing post-processing guardrails, and managing workflow versioning. Responsibilities include designing and building agentic systems that turn LLMs into dependable tools with retrieval, tool use, agentic reasoning, and structured outputs; collaborating with ML and infra engineers to scale and optimize workflows; writing high-quality modular code; making major architectural decisions; driving rigorous evaluation; leveraging frontier capabilities to prototype with new models and open-source tools; and continuousl