Software Engineer, Full Stack (Agentic AI)
$140,000–$200,000 year
HybridSan Francisco, California, United States
Job Summary
Talk directly to customers to turn review workflows into agent capabilities, generating dashboards, writing analysis scripts, and surfacing insights from telemetry. Design, ship, and operate agentic systems that reason over large-scale time-series data and hardware domain context. Build tool interfaces, sandboxed execution environments, and custom compaction algorithms to ensure agent dependability. Develop and maintain the MCP server, design APIs powering agentic capabilities, and run agents reliably at scale across cloud and on-prem environments. Construct frontend surfaces and evaluation suites to measure agent effectiveness, while integrating and assessing frontier models. This product engineering role focuses on making agents dependable through tool design, context management, and observability, with opportunities to own a product area from MVP through iteration.
Required Qualifications
- 3+ years of professional software engineering experience
- Get excited about owning a product area: talking to customers, deciding what to build, and shipping it
- Have built frontend web applications with technologies like React, NextJS, or similar
- Have built APIs (REST, gRPC, etc.) or backend services with technologies like Go, Python, Rust, or similar
- Are curious about new AI products: you try new agents, models, and features as they ship, and have opinions about what makes them good
- Must be a U.S. citizen, lawful permanent resident, or protected individual such as an asylee or refugee in compliance with ITAR (International Traffic in Arms Regulations) / EAR (Export Administration Regulations) regulations
Desired Qualifications
- Shipped products to users at scale: large data volumes, significant active user counts, or deep technical complexity
- Shipped LLM-powered features
- Built agentic systems: multi-step tool use, planning loops, context management, and evals
- Designed tool ecosystems for agents, including MCP
- Worked with sandboxed or isolated execution of generated code
- Operated services in production (Kubernetes, observability, incident response)
- A personal ecosystem of AI dev tooling: custom agents, skills, scripts, or workflows built to ship faster
- A background in time-series data, scientific computing, or hardware test and telemetry
- Built internal agentic tooling that accelerates an engineering org
Hiring someone like this?
Get your role in front of qualified candidates on Sorce.