Founding LLM Inference Engineer

Full-time | On-site | San Francisco, CA

Compensation: $200K – $300K + 0.10%–1.00% Equity

About the Role

We’re looking for a Founding LLM Inference Engineer to architect and optimize large-scale inference systems powering cutting-edge AI applications. You’ll be building the backbone of an AI platform used by top enterprises, with a focus on performance, scalability, and reliability.

This is a hands-on, high-impact role where you’ll collaborate closely with research and product teams, moving fast to bring breakthrough model capabilities into production. If you’re excited about low-latency systems, high-throughput pipelines, and deploying bleeding-edge LLMs, this role is for you.

Tech stack: Python, CUDA, LLMs, API integrations, TGI, vLLM, TensorRT-LLM

What You’ll Do

• Architect and implement scalable inference systems for state-of-the-art models
• Optimize infrastructure for high throughput and low latency at scale
• Develop and integrate advanced inference optimization techniques
• Collaborate with research teams to productionize new model capabilities
• Build developer tools and infra to support rapid experimentation and deployment

What We’re Looking For

• Deep expertise in LLM inference, optimization, and deployment at scale
• Strong background in Python and GPU programming (CUDA)
• Experience with serving frameworks (TGI, vLLM, TensorRT-LLM)
• Proven track record of shipping production-grade AI systems
• Excitement about building foundational infra at an early-stage AI startup

Benefits

• Competitive salary + equity (0.10%–1.00%)
• Health, dental, and vision insurance
• Daily team lunches and wellness stipend
• Unlimited PTO + flexible parental leave
• On-site role in San Francisco (5 days a week)

👉 Ready to take the next step?

Apply now or email Jenn at Recruiter@CareDynamicsFL.com to learn more.