Abridge is building an AI-powered platform that transforms medical conversations into structured clinical notes. This role focuses on designing and building the runtime, orchestration, and evaluation platform for agentic LLM-driven workflows. You will collaborate with researchers and product engineers to turn LLMs into dependable tools for healthcare.
Responsibilities
Design and build GenAI systems leveraging retrieval, tool use, agentic reasoning, and structured outputs.
Implement a highly reliable and scalable agent runtime with orchestration, shared state, memory, and tool-calling interfaces.
Build secure, sandboxed execution for agent actions and code, optimizing cold start, isolation, and observability.
Create unified interfaces for multiple model sizes and providers, and integrate with open tool ecosystems such as MCP-style connectors.
Develop an evaluation platform for online/offline assessments, A/B tests, safety checks, and regression gates.
Requirements
Experience building agent applications with tool-calling, context engineering, or open connector integrations.
Fluency with LLM APIs, prompting strategies, and orchestration patterns (e.g., LangChain, LlamaIndex, or custom pipelines).
Experience with retrieval systems, vector DBs, function calling, or agentic workflows.
LLM API is an AI infrastructure gateway that provides access to over 200 language models through a unified, OpenAI-compatible interface. It focuses on cost-effective integration, performance monitoring, and centralized API management for developers.