Senior Software Engineer

Swift Solar • San Carlos, CA

15d • $150,000 - $200,000 • Hybrid

About The Position

Swift Solar is on a journey to bring revolutionary clean-energy technology to market. We're in it for the long haul, with support from world-class investors. Join our extraordinary team building the cutting-edge solar technology that will power the future. You'll build AI products that assist scientists and accelerate our technical progress towards next-generation solar solutions. Every experiment we run costs tool time, materials, and scientists' attention, so choosing what to run next is one of the biggest levers on how fast our cells improve. You'll build the AI that helps our scientists make those choices. Our systems read scientific literature and query our lab and manufacturing data, then propose experiment plans that an automated optimizer uses to execute them. You will lead development of the planning and reasoning layer, which takes a research objective as input and uses a multi-agent system to guide our scientists and reach goals faster through the best selected experiment campaigns. Additionally, we need to measure what works and how frontier models and our own agents perform on problems our team has already worked through, so we can improve the system over time. This is also a place to experiment. When a promising new paper, model, or agent design comes out in AI for science, you can try it here on real problems instead of benchmarks someone else chose. You'll work with scientists who have spent years on perovskites, who know which questions matter and can tell you quickly whether an agent's answer makes sense. Because we develop the process and make the devices ourselves, the data, tools, and people who understand them live in the same company, so an idea can go from your screen to a measured result without waiting on anyone outside. Most of this is greenfield work, and speed matters. You'll get rough versions in front of scientists quickly, watch how they use them, and turn the ideas that hold up into production systems people rely on every day. Knowing when a prototype is ready to harden, and doing it without losing momentum, is a big part of the job.

Requirements

• 5+ years of professional software engineering experience, including systems that real users depend on
• Built full-stack web applications, with a Python backend and a TypeScript/JavaScript frontend (React, Vue, Svelte, or similar)
• Built applications on frontier LLMs through their APIs, such as agents, multi-step orchestration (e.g., LangGraph), or systems where models call tools
• Can take an idea from a quick prototype to a production system that people depend on
• Use AI coding tools like Claude Code every day, and can tell when what they produce is wrong
• Have a CS degree or a comparable record of open-source or portfolio work
• Write documented, tested code and are comfortable working in a shared codebase with git
• Can explain technical tradeoffs to scientists who aren't software engineers
• Take initiative and work independently
• Are coachable and comfortable when priorities change quickly
• Are kind, empathetic, conscientious, and motivated to make an impact on climate change

Nice To Haves

• Experience with multi-agent systems, especially ranking, review, or memory between runs
• Experience building evaluations or benchmarks for LLM agents
• Experience designing complex software architecture and leading projects end-to-end without much oversight
• Familiarity with Bayesian optimization, surrogate models, fine-tuning of open-weights models, or reinforcement-learning environments
• Experience analyzing and plotting scientific data
• An interest in science, shown through conferences, side projects, or papers (a science background is not required)
• Experience getting skeptical users to adopt internal tools
• Experience with SQL or database administration, AWS, Azure, or GCP, or CI/CD
• Experience working at a startup

Responsibilities

• Lead development of the planning and reasoning layer, which takes a research objective as input and uses a multi-agent system to guide scientists and reach goals faster through the best selected experiment campaigns.
• Measure what works and how frontier models and our own agents perform on problems our team has already worked through, so we can improve the system over time.
• Hold AI-written code to a high bar. Critically review the output and keep the codebase documented and tested.
• Help keep existing data systems running, including the pipeline that brings instrument data into our database.
• Review code across the team, and help hire and mentor new engineers as the team grows.
• Write about what we learn for our public whitepaper series and, when the work holds up, publish it in papers and present it at conferences.

Benefits

• Competitive package including salary, equity, and benefits
• 100% of your monthly premiums for HMO / PPO group healthcare plan options covered
• 75% of your dental and vision insurance premiums covered
• 401(k) matching
• Clean commuter benefits
• Meaningful equity
• Support in attending conferences
• Support in taking online courses

What This Job Offers

• Job Type: Full-time
• Career Level: Senior
• Education Level: Associate degree