Remote Real-Time AI Inference Engineer

Coinscapture; Northern (KY); Remote; USD 120,000 - 180,000; Full time

Benefits offered by this job

Remote work

Job summary

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

You will thrive by deploying state-of-the-art models, optimizing latency and throughput, and building tooling to help researchers ship new models safely and efficiently.

Qualifications

• Experience deploying and serving ML models in production, latency-sensitive or real-time apps.
• Strong engineering skills in GPU programming and inference optimization (CUDA, Triton, TensorRT, vLLM, SGLang).
• 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 the stack, including latency, throughput, and cost.
• Build high-performance serving systems for real-time, streaming workloads where every millisecond matters.
• Create tooling and infrastructure that lets researchers ship new models to production quickly, safely, and with confidence in their performance characteristics.

Skills

Production ML deployment

GPU programming

Inference optimization

Profiling & bottleneck diagnosis

Research-to-production handoff

Education

No degree required

Tools

CUDA

TensorRT

Triton

vLLM

SGLang

Job description

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

You will thrive by deploying state-of-the-art models, optimizing latency and throughput, and building tooling to help researchers ship new models safely and efficiently.