Senior ML Engineer: Production Inference & Optimization

Cloudflare; Greater London; Hybrid; GBP 110,000 - 140,000; Full time

Job summary

Cloudflare in London is seeking an ML engineer to define how machine learning models run across Cloudflare’s global network. You’ll collaborate with systems engineers, product teams, hardware partners, and AI/ML engineers to deploy models with low latency, strong reliability, and efficient resource use in production.

You’ll focus on benchmarking, evaluation, and tooling to help Cloudflare and its customers ship AI applications at internet scale.

Qualifications

• Experience building, optimizing, and operating ML models in production.
• Proficiency with Python and ML frameworks (PyTorch, TensorFlow, JAX).
• Hands-on inference optimization for large-scale models (quantization, batching, caching).
• Experience with model serving runtimes (TensorRT-LLM, ONNX Runtime, Triton).
• Familiarity with LLMs, speech/vision models, embeddings, multimodal modeling.

Responsibilities

• Develop, optimize, and productionize ML models for Cloudflare’s serverless inference platform.
• Build benchmarking/evaluation frameworks for latency, throughput, and cost efficiency across model families.
• Improve inference performance via quantization, batching, caching, and runtime tuning.

Skills

Python

PyTorch

TensorFlow

JAX

LLMs

Inference optimization

Model deployment

Performance tuning

Mentoring

Distributed systems

Tools

SGLang

vLLM

TensorRT-LLM

ONNX Runtime

Triton

llama.cpp

Job description

Cloudflare in London is seeking an ML engineer to define how machine learning models run across Cloudflare’s global network. You’ll collaborate with systems engineers, product teams, hardware partners, and AI/ML engineers to deploy models with low latency, strong reliability, and efficient resource use in production.

You’ll focus on benchmarking, evaluation, and tooling to help Cloudflare and its customers ship AI applications at internet scale.