Senior AI Engineer

At Weave, our mission is to evolve how therapeutic knowledge is captured, transformed, and communicated throughout drug development. We do this by equipping human experts with AI instruments to enable drugs to be brought to patients as rapidly, safely, and inexpensively as possible.

The Weave Platform streamlines regulatory workflows from start to finish by intelligently, creatively, and effectively infusing every step with AI. Together with our customers, Weave is designing and building the AI workbench for the entire therapeutic lifecycle.

We’re seeking a hands-on AI engineer who can bridge the gap between data and biomedical expertise while delivering robust backend code. Your primary focus will be building the LLM-facing components of our backend service, while ensuring the AI models consistently produce high-quality content under real-world load. 

The ideal candidate thrives in the full development cycle: taking concepts from initial conception through rigorous experimentation and testing, all the way to production deployment. You won't get lost in low-ROI side quests, but instead will maintain velocity with unwavering focus on the core value of your tasks.

We value pragmatic problem-solving over flashy technology and buzz words, robustly tested solutions over demoware. We're building solutions that actually work—simple, thoroughly tested, and rock-solid reliable. If you believe the best technology is the one that consistently delivers results, you'll fit right in.

• Writing production-ready backend code for LLM-facing components of our backend service
• Writing tooling for automating the testing of LLM-in-the-loop code
• Designing and validating LLM-based solutions and proving their effectiveness with real data and meaningful metrics
• Developing test metrics for key functionality

• History of working at early-stage, product-based startups (<50 people)
• Scientist by disposition (and ideally by training); holds background knowledge or education in the biomedical space
• Extensive knowledge of LLMs in production
• Directly interacting with LLMs without abstraction libraries
• Humble, hungry, and smart
• Able to move quickly on tasks while producing high-quality results
• Pragmatic, analytical thinker. Efficient decision maker
• Bonus: work with web services and frameworks
• Bonus: work with ORMs
• Bonus: knows SQL