Senior ML Systems Engineer — Rust & Distributed Infra

UiPath, Inc.; Greater London; Hybrid; GBP 100,000 - 180,000; Full time

Job summary

UiPath, Inc. is seeking a systems-focused engineer to advance the Machine Learning Services platform.

You will design, implement, and operate core infrastructure handling high-volume inference and multi-tenant workloads across Rust, Python, and cloud environments. Join a quick-moving, growth-focused team focused on distributed systems, Kubernetes orchestration, and performance-tuned GPU inference (ONNX) in production, while shaping robust, scalable architecture and contributing to a culture of

Qualifications

• 5+ years of engineering experience in large-scale, distributed services.
• Proficiency in systems-level languages (Rust, C++, Go) and strong Python skills.
• Experience with cloud ecosystems and containerization (Docker, Kubernetes).
• Strong understanding of concurrency and asynchronous programming.
• Ability to design robust architectures and communicate trade-offs.

Responsibilities

• Design, build, and operate the core MLS platform and its Rust-based API gateway, Python ML compute workers, and the distributed job queue.
• Address hard concurrency, performance, and distributed systems challenges for high-volume workloads.
• Collaborate with product and ML science teams to bring diverse models to life.
• Develop storage abstractions over cloud object stores with garbage collection and sharding.

Skills

Rust

C++

Go

Python

Distributed systems

Concurrency

Algorithm design

Education

Bachelor's degree in Computer Science or related field

Tools

Docker

Kubernetes

Azure

AWS

GCP

ONNX

Job description

UiPath, Inc. is seeking a systems-focused engineer to advance the Machine Learning Services platform.

You will design, implement, and operate core infrastructure handling high-volume inference and multi-tenant workloads across Rust, Python, and cloud environments. Join a quick-moving, growth-focused team focused on distributed systems, Kubernetes orchestration, and performance-tuned GPU inference (ONNX) in production, while shaping robust, scalable architecture and contributing to a culture of