Latest AI JobsBrowse Jobs
Inworld AI logo

Staff / Principal Machine Learning Engineer, Serving - UK

Inworld AIUKML Engineering
Apply on company site
Salary
£140K - £200K GBP
Job type
Full-time
Posted
7 Apr 2026
Status
Open · checked 7d ago

About this role

Role Overview

The Staff / Principal Machine Learning Engineer, Serving position at Inworld AI is a full-time engineering role located in the United Kingdom. This position suits an experienced technical professional who wants to build high-performance infrastructure for realtime artificial intelligence and large-scale language model serving.

Key Responsibilities

Take machine learning models from the research team, containerize them, optimize serving, and ensure reliable production operations.
Build and scale distributed systems capable of reliably handling thousands of concurrent connections and multi-GPU or multi-node inference.
Profile code and optimize performance for NVIDIA GPUs using advanced systems programming.
Apply techniques such as quantization, distillation, caching strategies, continuous batching, paged attention, and speculative decoding.
Design custom load balancing and manage orchestration utilizing tools like Kubernetes and Ray.

Requirements

Deep understanding of modern serving frameworks and techniques including vLLM or TRT-LLM.
Proficiency in C++, CUDA, Rust, or highly optimized Python.
Experience with distributed systems and scaling using Kubernetes, Ray, and multi-GPU environments.
Background featuring a PhD in Computer Science, Physics, Math, or equivalent practical experience building backend or machine learning systems.
Candidates must already possess the legal right to work in the United Kingdom, as visa sponsorship is unavailable for this specific UK-based opening.

Skills and Tools

Python
Kubernetes
Rust
C++
CUDA
Ray
LLM serving frameworks like vLLM and TRT-LLM

Salary and Benefits

The base salary range for this full-time position is £140,000 to £200,000 per year. In addition to base pay, total compensation includes equity and benefits. Individual compensation is determined based on work location, level, competencies, experience, and business needs. For candidates interested in relocating to the San Francisco Bay Area in the future, full United States visa and relocation support may be provided subject to business needs and work authorization requirements.

About the Company

Inworld AI is a research lab and inference provider focused on realtime artificial intelligence for consumer-facing applications. The organization builds first-party speech models, serves large language models, and runs inference for modular APIs supporting high-volume workloads across companions, healthcare, fitness, education, and media. Backed by investors such as Lightspeed Venture Partners, Section 32, Kleiner Perkins, Microsoft’s M12, Founders Fund, Meta, and Stanford, Inworld technology has powered applications for NVIDIA, Microsoft Xbox, Niantic, and others. The company has been recognized by CB Insights as one of the 100 most promising AI companies globally and named one of LinkedIn’s Top 10 Startups in the USA.

How to Apply

Interested candidates should review the job details and submit their application directly on the official company careers page.

Skills and tech stack

Questions candidates ask

What is the salary range for the Staff / Principal ML Engineer role?

The base salary range spans from £140,000 to £200,000 per year, supplemented by equity and benefits.

Where is this position located?

This role is based in the United Kingdom.

Is visa sponsorship available for this UK role?

No, visa sponsorship is not available for this role, and candidates must already hold the legal right to work in the United Kingdom. However, future relocation to the San Francisco Bay Area with visa support may be available for interested candidates depending on business needs.

What technical skills are required?

Required skills include Python, Kubernetes, Rust, C++, CUDA, Ray, and experience with LLM serving frameworks like vLLM or TRT-LLM.

What kind of company is Inworld AI?

Inworld AI is an inference provider and research lab specializing in realtime artificial intelligence for consumer applications, serving over 10 trillion LLM tokens per month.

Ready to apply?

The application is on the official Inworld AI careers page.

Apply on company site