Latest AI JobsBrowse Jobs
E

Research Engineer - Inference

ElevenLabsUnited KingdomResearch & Research Engineering
Apply on company site
Salary
Not listed
Job type
Full-time
Work mode
Remote
Posted
28 Aug 2026
Status
Open · checked 7d ago

About this role

Role Overview

The Research Engineer - Inference role at ElevenLabs involves deploying and optimizing frontier artificial intelligence models for production environments globally. This position is ideal for enthusiastic engineers who want to bridge the gap between experimental research breakthroughs and real-time products utilized by millions of users.

Key Responsibilities

Own the end-to-end systems that transition research checkpoints directly into serving infrastructure for live deployment.
Optimize inference performance across the technology stack by targeting latency, cost, and throughput.
Utilize optimization methodologies including quantization, model distillation, KV-cache optimization, custom kernels, and advanced batching strategies.
Build and fine-tune high-performance serving architectures designed specifically for real-time and streaming workloads.
Design and develop internal tooling and infrastructure that enable researchers to push new models to production safely, rapidly, and with high reliability.

Requirements

Demonstrated ability to solve challenging technical problems through tangible artifacts like GitHub contributions, past projects, or designs.
Practical background in deploying and serving machine learning models within production environments, particularly for latency-critical or real-time use cases.
Robust software engineering competencies focused on GPU programming and inference optimization.
Familiarity with tools, frameworks, and languages such as CUDA, Triton, TensorRT, vLLM, or SGLang.
Capability to independently profile, troubleshoot, and resolve system bottlenecks spanning from model architectures and custom kernels down to orchestration.

Skills and Tools

GPU Programming
Inference Optimization
CUDA and Triton
TensorRT
vLLM and SGLang
Serving Infrastructure and Profiling

Salary and Benefits

Professional development support through an annual discretionary learning and development stipend.
An annual discretionary social travel stipend to facilitate in-person meetings with colleagues.
Participation in annual company-wide international offsite events.
A monthly co-working stipend for team members situated away from primary office hubs.

About the Company

ElevenLabs is an artificial intelligence research and product organization established in January 2023 with the release of the initial human-like AI voice model. The company creates platforms across voice, audio, agents, and creative generation, serving millions of users and numerous enterprises globally. Backed by major investors such as Andreessen Horowitz, Sequoia, and ICONIQ Growth, the organization operates with a high-velocity, autonomous, and AI-first methodology.

How to Apply

Interested candidates should visit the official ElevenLabs careers page to submit their application.

Questions candidates ask

Is this position remote?

Yes, this role is remote and can be performed globally, with optional access to office locations in London, New York, San Francisco, and Warsaw.

What specific technical areas are the focus of this role?

The position focuses on deploying frontier AI models, optimizing inference performance, reducing latency, and building high-performance serving infrastructure.

Are formal degrees or certifications required?

No formal certifications or degrees are required. Candidates are evaluated based on their ability to showcase problem-solving skills through past projects, designs, or GitHub contributions.

What technologies should candidates be familiar with?

Candidates should ideally have experience with GPU programming and serving tools such as CUDA, Triton, TensorRT, vLLM, or SGLang.

What perks does ElevenLabs provide for remote workers?

ElevenLabs provides a monthly co-working stipend for employees not located near main hubs, alongside annual discretionary stipends for social travel and professional development.

Ready to apply?

The application is on the official ElevenLabs careers page.

Apply on company site