Research Engineer - Inference

The role

You will deploy and optimize frontier AI models in production. You will own systems that turn research breakthroughs into real-time products and optimize inference performance across the stack.

What you will do

• Deploy state-of-the-art models to production
• Own the path from research checkpoint to serving infrastructure
• Optimize inference performance including latency, throughput, and cost
• Use techniques such as quantization, distillation, KV-cache optimization, batching strategies, and custom kernels
• Build and tune high-performance serving systems for real-time, streaming workloads
• Create tooling and infrastructure for researchers to ship new models to production

Required qualifications

• Experience deploying and serving ML models in production, ideally for latency-sensitive or real-time applications
• Strong engineering skills in GPU programming and inference optimization (e.g., CUDA, Triton, TensorRT, or serving frameworks such as vLLM or SGLang)
• Capacity to autonomously profile, diagnose, and eliminate bottlenecks across the serving stack
• Ability to build tooling to measure bottlenecks

Nice to have

• Showcase solving impressively hard problems with artifacts such as past projects, designs, or GitHub contributions

Benefits

• Annual discretionary stipend for professional development
• Annual discretionary stipend to meet up with colleagues
• Annual team offsite
• Monthly co-working stipend if not located near a main hub

About the company

ElevenLabs is an AI research and product company transforming how we interact with technology. They serve millions of users and thousands of businesses through platforms like ElevenAgents, ElevenCreative, and ElevenAPI.