Software Engineer, Gen AI Platform

Abridge Abridge · Vertical AI · San Francisco, CA · Builder

Software Engineer, Gen AI Platform at Abridge, focusing on building the runtime, orchestration engine, and evaluation platform for agentic LLM-driven workflows in healthcare.

What you'd actually do

  1. Design and build GenAI systems that turn LLMs into composable, dependable tools—leveraging retrieval, tool use, agentic reasoning, and structured outputs.
  2. Design and implement a highly reliable and scalable agent runtime: orchestration, shared state and memory, tool-calling interfaces, and scheduling for cost, latency, and quality.
  3. Build secure, sandboxed execution for agent actions and code; optimize cold start, isolation, and observability.
  4. Ship unified interfaces for multiple model sizes and providers; integrate with open tool ecosystems such as MCP-style** **connectors for data and actions.
  5. Develop an evaluation platform for online and offline assessments, A/B tests, safety checks, and regression gates that improve agent reliability over time.

Skills

Required

  • 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 (e.g., semantic and lexical retrieval, vector DBs, efficient kNN), function calling, tool use, or agentic workflows.
  • Strong coding skills in one or more of: Python, Java, Go. Comfortable with service design, APIs, and data models for high-throughput systems.
  • Working knowledge of containers and kubernetes concepts. Familiarity with metrics, tracing, on-call rotations, and incident response practices.

Nice to have

  • Prior work on agent orchestration pipelines: task routing, planning, memory graphs, vector search, or browser automation.
  • Experience with evaluations, preference optimization, or RL to improve LLM reliability.

What the JD emphasized

  • agent applications with tool-calling
  • orchestration patterns
  • retrieval systems
  • agentic workflows
  • agent orchestration pipelines
  • evaluations

Other signals

  • agentic orchestration
  • LLM-driven workflows
  • evaluation platform