SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
Salary: USD 160,000 - 210,000 / annual
AssemblyAI builds Voice AI models powering the next generation of voice applications, serving 600M+ inference calls monthly and processing 1M+ hours of audio daily. The company is one of the most capital-efficient AI companies, with under 100 people generating roughly $600K ARR per employee.
You'll own the agent experience (AX) for AssemblyAI—how AI coding agents like Claude Code, Cursor, and Codex discover, integrate, and debug the platform. This is a new and rapidly growing area with significant opportunity to define the discipline.
Key responsibilities:
- Treat coding agents as a first-class user alongside humans using the dashboard and Playground
- Build and maintain agent skills for core products (Speech-to-Text, Real-time, Dictation, Voice Agents, TTS, LLM Gateway)
- Extend the AssemblyAI MCP server and agent integrations, including OAuth and API key authentication
- Make docs, code samples, and llms.txt agent-ready so agents pick the right API, parameters, and patterns on the first try
- Tune system prompts, tool definitions, and agent instructions powering in-dashboard agent and onboarding flows
- Build evals and benchmarks that run real coding agents against real integration tasks, tracking success rate and time to first working call
- Scale the playbook across products
- Use AI tools as a core part of your workflow and help the rest of engineering build faster with agents
You'll work closely with senior engineers on the Product Engineering team with real ownership from day one and room to grow into leading AX as the area scales.
Requirements:
- 2+ years of professional software engineering experience with solid full-stack fundamentals (JavaScript and/or Python)
- Daily, hands-on use of coding agents such as Claude Code, Cursor, or Codex, with genuine curiosity about what makes them succeed or fail
- Some hands-on experience writing prompts, skills, tool definitions, or agent instructions (at work or in side projects), with interest in measuring them with evals rather than intuition
- Product sense for developer-facing work; you care whether the developer or their agent actually reaches a working integration
- Clear technical writing skills; much of this role involves writing that both agents and humans read
- Comfort with ambiguity and bias to ship; AX is a new discipline and you'll help define it alongside the team
Nice to have:
- Working knowledge of MCP, LLM tool calling, and how agents read docs and APIs
- Experience building or contributing to an MCP server, agent skill library, or coding agent plugin
- Developer relations, docs engineering, or SDK experience at an API-first company
- Experience with Voice AI, speech-to-text, or LLM APIs
- Shipped something that agents use in the wild with measurable before/after results
