Realtime AI Inference Engineer — Remote

AI Startups UK; United Kingdom; Remote; GBP 90,000 - 150,000; Full time

Benefits offered by this job

Annual discretionary stipend

Annual company offsite

Co-working stipend

Social travel

Job summary

ElevenLabs is hiring a Research Engineer to deploy and optimize frontier AI models in production. You will own the systems that turn research breakthroughs into real‑time products used by millions.

You thrive when deploying state‑of‑the‑art models and ensuring fast, scalable serving across the stack. You’ll focus on latency, throughput, and cost optimization, using techniques like quantization, batching, and custom kernels, while building tooling that helps researchers ship models safely and

Qualifications

• Experience deploying and serving ML models in production, especially for latency‑sensitive or real‑time apps.

Responsibilities

• Deploy state‑of‑the‑art models to production and own the path from research checkpoint to serving infrastructure.
• Optimize inference performance across the stack (latency, throughput, cost) with techniques like quantization and batching.
• Build and tune high‑performance serving systems for real‑time, streaming workloads where every millisecond matters.
• Create tooling to help researchers ship models to production quickly and safely.

Skills

ML deployment

GPU programming

Performance profiling

Serving systems

Tools

CUDA

Triton

TensorRT

vLLM

Job description

ElevenLabs is hiring a Research Engineer to deploy and optimize frontier AI models in production. You will own the systems that turn research breakthroughs into real‑time products used by millions.

You thrive when deploying state‑of‑the‑art models and ensuring fast, scalable serving across the stack. You’ll focus on latency, throughput, and cost optimization, using techniques like quantization, batching, and custom kernels, while building tooling that helps researchers ship models safely and