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, Technology, Information and Internet.

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 in San Francisco, CA. You'll build and operate the agent layer that powers AI-native creative products — focusing on LLM-powered agents, tool orchestration, memory/context management, and the production systems that make those agents reliable and delightful for real users.

---

What You’ll Do

• Build and extend the agent harness that powers conversational and autonomous creative workflows: tool use, context/memory management, multi-step planning, and sub-agent orchestration.
• Implement and maintain MCP servers and CLI tooling that connect agents to internal services, external model vendors, and creative asset pipelines.
• Author reusable Agent Skills and structured workflows so agents can handle complex, multi-step creative tasks (scene planning, storyboarding, asset generation, revision loops).
• Contribute to evaluation frameworks and observability to detect regressions and measure agent quality in production.
• Ship polished, production frontend experiences (React / Next.js) that expose agent-driven capabilities to end users.
• Make pragmatic trade-offs between speed, correctness, and scalability — and communicate trade-offs clearly across engineering and product teams.
• Partner with product, design, and GTM to translate user needs into technical solutions and measurable outcomes.
• Track the fast-moving agent ecosystem (MCP, Agent Skills, orchestration frameworks) and bring best-in-class ideas into the stack.

---

What We’re Looking For

Core requirements

• 2+ years of full‑stack engineering experience shipping production software.
• Hands-on experience building LLM-powered agents or agent-driven applications that reached real users.
• Working familiarity with agent harness concepts: tool use, context/memory management, multi-step planning, or sub-agent orchestration.
• Strong data modeling and schema design skills for real product use cases.
• Experience using AI-assisted coding tools (e.g., Claude Code, Codex, Cursor) as a core part of your workflow and opinionated thoughts on their strengths/limits.
• Product sense — you care about trust, reliability, and a delightful user experience, not only correctness.
• Clear written and verbal communication — able to explain agent behavior and trade-offs to non-engineers.

Nice to have

• Experience authoring reusable Agent Skills or structured agent workflows.
• Practical experience building MCP servers or CLI tooling for agents.
• Exposure to agent orchestration frameworks (Claude Agent SDK, LangGraph, or similar) or LLM evaluation/observability tooling.
• Hands‑on experience with image/video generation models or creative ML tooling.
• Startup or 0→1 product experience (side projects count).

---

Compensation & Benefits

• Total compensation target: $300k+ (base, bonus, equity) — package details vary by role and candidate.
• Meaningful equity — ownership in what you build.
• High autonomy and rapid growth environment.
• Visa sponsorship available.

(Note: Confidential Client provides full benefits details during interview. Exact base salary range was not provided in the source posting.)

---

Location & Work Setup

• San Francisco, CA — Bay Area preferred; hybrid options available.
• This role expects close collaboration with product and design teams; partial remote work may be considered depending on team needs and immigration status.

---

What Success Looks Like (3–6 months)

• You’ve shipped a production agent workflow used by real users.
• You’ve improved part of the harness, a set of Agent Skills, or the evaluation loop and can point to a moved metric.
• You own at least one area of the agent stack end-to-end and are the go-to person for it.
• You’ve formed tight feedback loops with design, founders, and users and are proactively proposing improvements.

---

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.