Remote Engineering Lead, AI Figure Platform

BioRender; San Francisco (CA); Remote; USD 180,000 - 250,000; Full time

Job summary

BioRender is building an AI figure agent to create scientific figures across pathways, protocols, and posters. You will lead the core agent platform, shaping architecture and orchestration to ship reliable, high-quality AI-powered figures for millions of researchers.

You will guide a small engineering team, drive evaluations of LLMs/VLMs, and collaborate with Product and Creative teams to translate feedback into tangible improvements.

Qualifications

• Experience leading engineers and setting technical direction for complex, production-grade AI systems.
• Experience architecting and shipping an agent or multi-agent orchestration platform to production.
• Hands-on with frontier models and VLMs, including model routing and cost/quality trade-offs.

Responsibilities

• Lead a small engineering team responsible for the core agent platform, including architecture and orchestration.
• Continuously improve figure quality through evaluations, experimentation, and real user feedback.
• Evaluate and benchmark frontier LLMs and VLMs for scientific accuracy, reasoning, and visual understanding.
• Optimize model selection and routing to balance quality, cost, speed, and reliability.
• Build shared AI infrastructure and tooling to debug agent behavior and ship improvements faster.
• Define quality standards and establish monitoring, alerting, and triage for agent performance.
• Partner with Product and Creative teams to translate feedback into measurable improvements.

Skills

Leadership

Agent orchestration

AI systems architecture

Model routing

Communication across teams

Experimentation & evaluation

People management

Education

Science background (nice to have)

Tools

AgentCore

Job description

BioRender is building an AI figure agent to create scientific figures across pathways, protocols, and posters. You will lead the core agent platform, shaping architecture and orchestration to ship reliable, high-quality AI-powered figures for millions of researchers.

You will guide a small engineering team, drive evaluations of LLMs/VLMs, and collaborate with Product and Creative teams to translate feedback into tangible improvements.