E
Research Engineer - Inference
Contract type
Ongoing
Work mode
Remote · Worldwide
Experience
3 years
Job description
Research Engineer on ElevenLabs' research team focused on deploying and optimizing frontier AI models in production, owning the path from research checkpoint to serving infrastructure. The role is remote and can be executed globally.
At a glance
- Work mode
- Remote · Worldwide
What you'll do
- Deploying state-of-the-art models to production and owning the path from research checkpoint to serving infrastructure
- Optimizing inference performance across the stack, including latency, throughput, and cost, using techniques such as quantization, distillation, KV-cache optimization, batching strategies, and custom kernels
- Building and tuning high-performance serving systems for real-time, streaming workloads where every millisecond matters
- Creating tooling and infrastructure that lets researchers ship new models to production quickly, safely, and with confidence in their performance characteristics
What we're looking for
- Experience deploying and serving ML models in production, ideally for latency-sensitive or real-time applications
- Strong engineering skills in GPU programming and inference optimization (e.g., CUDA, Triton, TensorRT, or serving frameworks such as vLLM or SGLang)
- The capacity to autonomously profile, diagnose, and eliminate bottlenecks across the serving stack, from model architecture to kernels to orchestration, and to build the tooling to measure it
- No formal certifications or degrees required; showcase solving impressively hard problems with artifacts such as past projects, designs, or GitHub contributions
Your team
research team
Benefits
- Innovative culture: part of a generational opportunity to define the trajectory of AI
- Growth paths: countless opportunities to drive impact beyond immediate role and responsibilities
- Learning & development: annual discretionary stipend for professional development
- Social travel: annual discretionary stipend to meet up with colleagues each year
- Annual team offsite: entire team gathers in a new location each year (past offsites included Croatia, Italy and Cancún)
- Co-working: monthly co-working stipend if not located near one of the main hubs
Apply
About ElevenLabs
AI research and product company transforming how we interact with technology
ElevenLabs launched in January 2023 with the first human-like AI voice model. It serves millions of users and thousands of businesses, from fast-growing startups to large enterprises. Its platforms are ElevenAgents (voice and chat agents at scale), ElevenCreative (speech, music, image, and video generation across 70+ languages), and ElevenAPI (access to AI audio foundational models).
Key facts
- 2023
- AI research and product
- Launched in January 2023 with the first human-like AI voice model
- Serves millions of users and thousands of businesses
- Raised $781M in funding
- Last valuation was $22B
- Expanded from voice into three main platforms: ElevenAgents, ElevenCreative, ElevenAPI
- Team includes researchers, engineers, and operators, IOI medalists and ex-founders
Partners & customers
Deutsche TelekomMetaAndreessen HorowitzICONIQ GrowthSequoia
What they value
- High-velocity: rapid experimentation, lean autonomous teams, and minimal bureaucracy
- Impact not job titles
- AI first
- Excellence everywhere
- Global team: prioritize talent, not location