Senior ML Engineer — Production Inference & Optimization

Hc1; Greater London; Hybrid; GBP 90,000 - 150,000; Full time

Job summary

Cloudflare is expanding its ML capability in London, building and optimizing production ML models for a serverless inference platform. You’ll collaborate with systems engineers, hardware partners, and AI/ML teams to deliver low-latency, reliable models that scale across Cloudflare’s global network.

You’ll focus on benchmarking, inference optimization, validation, and tooling to empower Workers AI and customer deployments.

Qualifications

• Experience building production ML models with focus on reliability and performance.
• Proficiency in Python and ML frameworks (PyTorch/TF/JAX) for model development.
• Hands-on experience with inference optimization techniques (quantization, batching, caching).
• Familiarity with distributed systems, networking, or serverless platforms.
• Track record leading complex technical projects and mentoring engineers.

Responsibilities

• Develop, optimize, and productionize ML models for Cloudflare’s serverless inference platform.
• Build benchmarking and evaluation frameworks for latency, throughput, and cost efficiency across model families.
• Improve inference performance via quantization, batching, caching, and runtime tuning.
• Collaborate with systems engineers to deploy models across a heterogeneous GPU fleet and accelerators.
• Improve model deployment workflows, validation, rollout safety, observability, and reliability.
• Work with product/engineering teams to translate customer needs into scalable ML capabilities for Workers AI.
• Mentor engineers and contribute to technical direction and engineering standards.

Skills

Python

ML Frameworks (PyTorch/TF/JAX)

Inference optimization

Distributed systems

Mentoring engineers

Tools

SGLang

vLLM

TensorRT-LLM

ONNX Runtime

Triton

llama.cpp

Job description

Cloudflare is expanding its ML capability in London, building and optimizing production ML models for a serverless inference platform. You’ll collaborate with systems engineers, hardware partners, and AI/ML teams to deliver low-latency, reliable models that scale across Cloudflare’s global network.

You’ll focus on benchmarking, inference optimization, validation, and tooling to empower Workers AI and customer deployments.