About Careertakes

👉 Important disclosure: Careertakes is a third-party recruiting platform supporting this hiring process. If selected, you will be employed directly by our client, Software Development.

Applicants for this role may also receive access to additional matched opportunities through the Careertakes platform.

---

Role overview

Confidential Client is hiring a Software Engineer, Agent Experience to own how coding agents integrate with their voice- and LLM-powered APIs. This role focuses on making machine-readable docs, agent skills, SDK examples, prompts, and integrations so an agent (Claude Code, Cursor, Codex, etc.) can take a developer from zero to a working, production-ready integration on the first try.

This is a full-time role based in San Francisco, CA. The hiring organization is listed as Confidential Client (via Careertakes). Candidates should be comfortable working in a fast-moving, product-focused engineering team and using AI tools as part of the engineering workflow.

---

What You’ll Do

• Drive the agent experience — treat coding agents as first-class users alongside human developers.
• Build and maintain agent skills for core products (speech-to-text, real-time, TTS, voice agents, LLM gateway).
• Extend and improve MCP server and agent integrations, including auth patterns (OAuth, API keys).
• Make docs and code samples machine- and agent-ready (llms.txt, quickstarts, SDK examples).
• Tune prompts, system instructions, and tool definitions that power agent onboarding and flows.
• Build evaluation suites and benchmarks to measure agent success rate, time to first working call, and activation from agent-driven signups.
• Scale successful patterns across products and features.
• Use AI tooling to accelerate engineering work and help teammates adopt agent-driven workflows.

---

What You’ll Need

• 2+ years of professional software engineering experience with solid full-stack fundamentals (JavaScript and/or Python).
• Daily, hands-on experience using coding agents such as Claude Code, Cursor, or Codex and curiosity about what makes them succeed or fail.
• Hands-on experience writing prompts, skills, tool definitions, or agent instructions (professional or side projects).
• Product sense for developer-facing experiences — you care whether an agent or developer actually gets to a working integration.
• Clear technical writing skills; much of the role is writing consumable docs and machine-readable artifacts.
• Comfort with ambiguity and a bias to ship in a newly forming discipline.

---

Nice to Have

• Working knowledge of MCP, LLM tool calling, and how agents parse 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.
• Examples of shipped work used by agents in production (before/after metrics preferred).

---

Compensation & Location

• Location: San Francisco, CA (role supports telecommute/remote workflows).
• Employment type: Full-time.
• USD salary range (as provided by the client): $160,000 - $210,000 per year.
  • This range is provided to comply with pay transparency requirements and represents the client’s stated range for U.S. candidates. Final salary will depend on experience, skills, and internal equity.

---

Additional notes (legal & process)

• You will be employed by Confidential Client; Careertakes assists as a third-party recruiter.
• The hiring process may use AI tools to assist with screening; final decisions are made by people.
• Confidential Client and Careertakes follow applicable U.S. employment laws, including state-level pay transparency and non-discrimination requirements.
• Reasonable accommodations are available for applicants with disabilities; please notify the recruiter or Careertakes if you need assistance.

---

Equal Opportunity & Hiring Transparency

Careertakes and our client are Equal Opportunity Employers committed to building a diverse and inclusive workforce. We prohibit discrimination or harassment of any kind. To support a fair and efficient hiring process, AI tools may be used to assist with application review or resume screening. These tools do not replace human decision-making. Final hiring decisions are made by people.

If you have questions about how your data is used, please contact us directly.