Machine Learning Engineer

Machine Learning Engineer - AI Infrastructure

Remote (Europe) | Up to €125K | $1B Valuation

A fast-growing AI infrastructure company valued at $1B is hiring a Machine Learning Engineer to help build autonomous control systems for cloud and AI infrastructure at scale.

The company is developing a Kubernetes-native automation platform designed to remove manual tuning from production Kubernetes environments by embedding intelligent decision-making directly into infrastructure. A key focus area is optimising LLM workloads and inference costs across cloud environments.

The Role

You will work on greenfield systems that automatically evaluate, route, and optimise large language model usage across cloud providers. The goal is to build infrastructure that can dynamically determine the most efficient way to run AI workloads without sacrificing output quality.

Key challenges include:

• Selecting the most cost-efficient model for each prompt while maintaining quality
• Optimising cost per million tokens and reducing token waste in high-frequency prompts
• Identifying API key inefficiencies and improving utilisation
• Designing fine-tuning strategies that balance performance and cost

What You’ll Be Doing

• Designing and building distributed inference and training pipelines in Python
• Working with vLLM, SGLang, TensorRT, and PyTorch
• Implementing inference optimisation techniques such as quantisation, reduced precision, and memory/init-time reduction
• Optimising networking for distributed ML workloads
• Tuning inference engines for production-scale AI systems

Tech Stack

Python, vLLM, SGLang, TensorRT, PyTorch

ClickHouse, PostgreSQL

GCP Pub/Sub

gRPC, REST APIs

Kubernetes across AWS, GCP, and Azure

GitLab CI/CD, ArgoCD

Prometheus, Grafana, Loki, Tempo

Details

• Location: Must be based in Europe (certain countries only...)
• Salary: Up to €125K
• Interview Process: 4 stages

This is an opportunity to work on cutting-edge infrastructure for large-scale AI systems, solving complex optimisation challenges at the intersection of ML, distributed systems, and cloud infrastructure.