Senior AI Engineer

Test Sprite is redefining software testing with AI. Our platform automates end-to-end testing for backend REST APIs and frontend web applications — using intelligent agents that can understand, navigate, and test real-world software the way a human would, but faster and 're well-funded, growing fast, and solving one of the biggest bottlenecks in modern software development: testing.

If you've ever shipped code and wished testing could just handle itself — that's what we're building.

We're hiring multiple Senior AI Engineers to design and build the AI systems at the heart of Test Sprite. You'll tackle some of the most interesting problems in applied AI today — from orchestrating autonomous agents that interact with live web applications to improving the accuracy of AI-generated test logic at scale.

You won't be fine-tuning models in a notebook. You'll be building production AI systems that developers rely on every day. This is a high-impact role on an agile, fast-moving team where your work will shape the product and the company's technical direction.

• Design, build, and iterate on AI systems that drive Test Sprite's core testing automation.
• Architect and implement agentic workflows that interact with real web applications and APIs.
• Develop and refine prompt engineering strategies, model orchestration, and evaluation pipelines.
• Improve the accuracy and reliability of AI-generated test plans and test code.
• Collaborate closely with engineering and product to turn research insights into production features.
• Evaluate and integrate new models, tools, and techniques as the AI landscape evolves.
• Contribute to system design decisions and help set the technical direction for AI at Test Sprite.

• 3+ years of professional software development experience.
• Solid hands-on experience designing and implementing AI systems (e.g., LLM-based applications, agentic systems, ML pipelines).
• Strong programming skills in Python, Type Script, or similar languages.
• Familiarity with LLM APIs (OpenAI, Anthropic, etc.), prompt engineering, and model evaluation.
• Experience building reliable, production-grade AI features — not just prototypes.
• Strong problem-solving skills and the ability to work autonomously in a fast-paced startup environment.
• Clear communication skills and a collaborative mindset.

• Familiarity with software testing concepts and workflows.
• Experience with agentic AI frameworks (e.g., Lang Graph, CrewAI) or building custom agent loops.
• Background in developer tools or devtools startups.
• Experience with fine-tuning, RAG, or vector search systems.

• Well-funded startup with a completed seed round, real customers, and a product in market.
• Work at the frontier of agentic AI — our product is the problem space everyone's talking about.
• High autonomy and direct impact — your work ships and matters.
• Hybrid work schedule based in Seattle, WA.
• Join a team that's building the future of how software gets tested — before everyone else catches up.