Remote Research Engineer: Real-Time AI Inference

ElevenLabs; Greater London; Remote; GBP 85,000 - 140,000; Full time

Benefits offered by this job

Innovation culture

Growth paths

Learning & development stipend

Social travel stipend

Annual company offsite

Co-working stipend

Job summary

ElevenLabs is seeking a Research Engineer to join our research team, focused on deploying and optimizing frontier AI models in production. You will own the systems that turn research breakthroughs into real-time products used by millions.

If you enjoy solving latency-sensitive challenges, you will work on inference performance, serving infrastructure, and tooling that helps researchers ship new models quickly, safely, and with confidence in their performance.

Qualifications

• Experience deploying and serving ML models in production.
• Strong engineering skills in GPU programming and inference optimization (CUDA, Triton, TensorRT, or serving frameworks).
• Ability to profile, diagnose, and eliminate bottlenecks across the serving stack and build tooling to measure it.

Responsibilities

• Deploy state-of-the-art models to production and own the path from research checkpoint to serving infrastructure.
• Optimize inference performance across latency, throughput, and cost.
• Build high-performance serving systems for real-time, streaming workloads.
• Create tooling and infrastructure to ship new models quickly and safely.

Skills

ML model deployment

GPU programming

Profiling & optimization

System design

Tools

CUDA

Triton

TensorRT

vLLM

SGLang

Job description

ElevenLabs is seeking a Research Engineer to join our research team, focused on deploying and optimizing frontier AI models in production. You will own the systems that turn research breakthroughs into real-time products used by millions.

If you enjoy solving latency-sensitive challenges, you will work on inference performance, serving infrastructure, and tooling that helps researchers ship new models quickly, safely, and with confidence in their performance.