Remote Real-Time Inference Engineer

Devconnectplatform; United States; Remote; USD 120,000 - 190,000; Full time

Benefits offered by this job

Annual discretionary stipend

Social travel stipend

Annual company offsite

Co-working stipend

Job summary

ElevenLabs is seeking a Research Engineer to join the research team focused on deploying frontier AI models in production, ensuring fast, reliable serving at scale.

You will own the systems turning research breakthroughs into real-time products, optimizing latency, throughput, and cost with techniques like quantization and KV-cache optimization. This remote role welcomes talent worldwide.

Qualifications

• Experience deploying and serving ML models in production.
• Strong engineering skills in GPU programming and inference optimization.
• Ability to profile bottlenecks across serving stack and build tooling.

Responsibilities

• Deploy state-of-the-art models to production and own the path to serving.
• Optimize latency, throughput, and cost across the stack.
• Build tooling and infrastructure for researchers to ship models quickly.

Skills

ML deployment

GPU programming

CUDA

Triton

TensorRT

vLLM

SGLang

Tools

Triton

TensorRT

CUDA

Job description

ElevenLabs is seeking a Research Engineer to join the research team focused on deploying frontier AI models in production, ensuring fast, reliable serving at scale.

You will own the systems turning research breakthroughs into real-time products, optimizing latency, throughput, and cost with techniques like quantization and KV-cache optimization. This remote role welcomes talent worldwide.