> Markdown version of [/jobs/ext/4650293-senior-software-engineer-agents](https://www.wearedevelopers.com/jobs/ext/4650293-senior-software-engineer-agents). Every page supports `.md` or `Accept: text/markdown`. Links point to the HTML versions so they work for humans too. Agent guide: [/agents.md](https://www.wearedevelopers.com/agents.md). --- # Senior Software Engineer (Agents) - **Company:** Recruiting from Scratch - **Location:** San Francisco, CA, United States (Remote available) - **Experience:** Expert - **Salary:** $180,000 - **Contract:** Permanent contract - **Skills:** Computer-Aided Design, Application Programming Interfaces (APIs), Artificial Intelligence, Software Applications, Systems Engineering, Software Quality, Code Review, Computer Engineering, Software Debugging, Desktop Computing, Distributed Systems, Python (Programming Language), Performance Tuning, Software Tools, Software Engineering, Systems Integration, Large Language Models, Reliability of Systems, Backend, Agentic-AI, LangSmith, Production Code, Observability for Autonomous Agents, Engineering Base, Programming Languages - **Published:** November 9, 2026 - **Apply:** https://www.careerbuilder.com/job-details/senior-software-engineer-agents-san-francisco-ca--54bdaa2e-fb9f-478b-83c8-8ad09f31d5fe ## About the Role Software Engineering, Software Agents, Software Engineering, Systems Engineering, Artificial Intelligence (AI) Agents, Engineering Software, Artificial Intelligence (AI), Product Development, Desktop PC, Computer Engineering, * 3-10 years of professional software engineering experience building, shipping, and maintaining production systems. * Strong computer science fundamentals and sound software engineering judgment. * Experience building backend systems, infrastructure, distributed systems, or complex software applications. * Comfortable owning technical problems end to end, from understanding requirements to implementation, testing, and production reliability. * Interested in AI agents and the engineering challenges involved in making them reliable, efficient, and useful in real-world environments. * Able to reason about multi-step workflows, state management, failure handling, concurrency, and system performance. * Comfortable working in a fast-paced, early-stage startup environment with significant individual ownership. Important: Prior experience building LLM agents is not required. The team is open to strong software engineers who have the fundamentals and genuine interest in developing expertise in agentic systems. Technical Skills Core requirements * Strong software engineering and computer science fundamentals. * Production experience with Python or another modern programming language. * Experience designing and maintaining production systems. * Strong understanding of backend systems, APIs, state management, and system reliability. * Ability to debug complex issues and reason through failure scenarios. * Good engineering judgment and code quality. Relevant areas of experience * Agentic systems, tool calling, and orchestration. * Distributed systems and workflow execution. * Context management, model routing, and multi-step task execution. * Evaluation frameworks, testing infrastructure, and benchmarking. * Performance optimization, latency reduction, and cost efficiency. * Desktop application automation or integrations with complex software. Preferred Background * Experience working with LLMs, AI agents, or model-powered applications. * Familiarity with agent observability and evaluation tools such as LangSmith or Logfire. * Experience with CAD, CAE, PLM, or other complex desktop engineering applications. * Experience with COM or desktop application integrations. * Exposure to enterprise environments, locked-down workstations, or on-premise deployments. * Experience building reliable systems that operate across multiple tools and long-running workflows. * Experience in an early-stage startup or a small, high-ownership engineering team. Working Style * Strong ownership mentality and ability to work independently. * Curious about how complex systems work and motivated to solve difficult engineering problems. * Comfortable working across technical and product boundaries. * Practical and outcome-oriented, with a focus on measurable product impact. * Excited to work closely with a small team in a fast-paced, in-person environment. * Interested in the real-world application of AI rather than purely research-oriented work. ## Description * Build and own core components of an agentic system, including tool calling, state management, context management, error recovery, and model routing. * Design reliable systems that can execute complex, multi-step workflows across desktop engineering applications. * Optimize agent performance across latency, reliability, and cost, including token efficiency and per-workflow budgets. * Build production systems that interact with real desktop applications in secure and restricted enterprise environments. * Own significant pieces of the agent infrastructure from design through implementation and production deployment. Evaluation & Workflow Coverage * Help design and develop evaluation infrastructure to measure agent performance against real-world engineering workflows. * Build reproducible and challenging benchmarks based on actual user requirements rather than purely synthetic tasks. * Work with domain experts and user researchers to understand engineering workflows and translate them into measurable evaluation cases. * Identify gaps in agent capabilities and systematically improve the percentage of workflows the system can complete end to end. * Measure success through task completion rates, workflow coverage, reliability, and token efficiency. Engineering Craft & Collaboration * Write high-quality, maintainable production code and contribute to thoughtful architectural decisions. * Participate in code reviews and help establish strong engineering standards across the team. * Collaborate with AI engineers, product, integration teams, researchers, and domain experts. * Work closely with customers during proof-of-concept engagements to understand real-world usage and improve agent behavior. * Help shape the technical direction of the core agent platform.