Research Engineer - Inference
ElevenLabs
Summary
We are looking for a Research Engineer to join the research team at ElevenLabs, focused on deploying and optimizing our frontier AI models in production. The quality of our models only matters if they can be served fast, reliably, and at scale. You will own the systems that turn research breakthroughs into real-time products used by millions.
Job description
About the Role
We are looking for a Research Engineer to join the research team at ElevenLabs, focused on deploying and optimizing our frontier AI models in production. The quality of our models only matters if they can be served fast, reliably, and at scale. You will own the systems that turn research breakthroughs into real-time products used by millions.
- Deploying state-of-the-art models to production and owning the path from research checkpoint to serving infrastructure.
- Optimizing inference performance across the stack, including latency, throughput, and cost, using techniques such as quantization, distillation, KV-cache optimization, batching strategies, and custom kernels.
- Building and tuning high-performance serving systems for real-time, streaming workloads where every millisecond matters.
- Creating tooling and infrastructure that lets researchers ship new models to production quickly, safely, and with confidence in their performance characteristics.
Requirements
We do not require any formal certifications or degrees. Instead, we are seeking enthusiastic engineers who can showcase solving impressively hard problems with artifacts such as past projects, designs, or GitHub contributions. Ideally, you bring:
- 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).
- The capacity to autonomously profile, diagnose, and eliminate bottlenecks across the serving stack, from model architecture to kernels to orchestration, and to build the tooling to measure it.
Location
This role is remote and can be executed globally. If you prefer, you can work from our offices in London, New York, San Francisco, and Warsaw.
Requirements
- 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).
- The capacity to autonomously profile, diagnose, and eliminate bottlenecks across the serving stack, from model architecture to kernels to orchestration, and to build the tooling to measure it.
Benefits
- Professional Development Stipend
- Annual Social Travel Stipend
- Annual Company Offsite
- Monthly Coworking Stipend
Company overview
ElevenLabs is a pioneering artificial intelligence company specializing in advanced voice technology and speech synthesis solutions. Founded in 2022 by former Google machine learning engineer Piotr Dąbkowski and ex-Palantir deployment strategist Mati Staniszewski, the company has rapidly emerged as a leader in AI-powered voice generation. Headquartered in London, ElevenLabs develops cutting-edge deep learning models that produce remarkably natural-sounding speech with emotional nuance and contextual awareness. The company's flagship products include text-to-speech software capable of synthesizing vocal emotion and intonation, voice cloning technology, AI dubbing tools supporting over 20 languages, and conversational AI platforms for creating interactive voice agents. With a valuation reaching $11 billion and backing from prominent investors including Andreessen Horowitz and Sequoia Capital, ElevenLabs serves over one million registered users worldwide. The company's technology enables applications across content creation, audiobook production, multimedia localization, and interactive voice interfaces, while also developing detection tools to identify AI-generated audio and address ethical concerns surrounding voice cloning technology.