Senior ML Engineer: Production Inference & Optimization

Cloudflare; United Kingdom; Hybrid; GBP 90,000 - 160,000; Full time

Benefits offered by this job

Stock options

Commuter program

Healthcare

Pension plans

Maternity & paternity leave

Wellbeing programs

Job summary

Cloudflare seeks experienced ML Engineers to define and optimize how models run across its global network. You will work with systems engineers, product teams, and AI/ML engineers to bring models into production with low latency and high reliability.

You will build benchmarking frameworks, improve serving performance, and develop tooling that helps Cloudflare and its customers deploy AI at Internet scale. Strong Python and ML framework skills are essential.

Qualifications

• Experience with large-scale inference serving frameworks or runtimes (SGLang, vLLM, TensorRT-LLM, ONNX Runtime, Triton, llama.cpp)
• Hands-on experience with inference optimization techniques for GPUs/specialized accelerators
• Experience building, optimizing, and operating ML models in production environments

Responsibilities

• Define how ML models run across Cloudflare’s network.
• Collaborate with systems engineers, product teams, and AI/ML engineers to productionize models with low latency
• Benchmark models, improve serving performance, validate quality, and build tooling for AI at Internet scale
• Develop, optimize, and productionize ML models for serverless inference platform focusing on performance and reliability
• Build benchmarking/evaluation frameworks for latency, throughput, and cost across model families
• Improve inference performance via quantization, batching, caching, compilation, and runtime tuning
• Partner with teams to integrate models into Cloudflare’s distributed inference infrastructure
• Drive model deployment workflows including validation, rollout safety, observability, and reliability
• Mentor engineers and guide production ML engineering practices

Skills

Inference serving

Model optimization

Quantization

Batching

Caching

Python

ML frameworks

Tools

SGLang

vLLM

TensorRT-LLM

ONNX Runtime

Triton

llama.cpp

Job description

Cloudflare seeks experienced ML Engineers to define and optimize how models run across its global network. You will work with systems engineers, product teams, and AI/ML engineers to bring models into production with low latency and high reliability.

You will build benchmarking frameworks, improve serving performance, and develop tooling that helps Cloudflare and its customers deploy AI at Internet scale. Strong Python and ML framework skills are essential.