Senior ML Engineer - Production AI at Internet Scale

Fdetimes; Austin, New York, San Francisco (TX, NY, CA); Hybrid; USD 185,000 - 254,000; Full time

Benefits offered by this job

Health insurance

Dental insurance

401(k) plan

Stock participation

Job summary

Cloudflare is seeking an experienced ML Engineer to define and optimize how machine learning models run across Cloudflare’s global network. You will work with ML researchers, systems engineers, and hardware partners to bring models to production with low latency and high reliability.

You will focus on benchmarking, inference optimization, and building tooling that enables Cloudflare and its customers to ship AI applications at internet scale.

Qualifications

• Proven experience building production ML models.
• Strong Python and ML framework knowledge (PyTorch, TensorFlow).
• Experience with large-scale inference and GPU optimization.

Responsibilities

• Develop production ML models for Cloudflare’s serverless inference platform.
• Build benchmarking and evaluation frameworks for latency, throughput, and cost.
• Improve inference performance via quantization, batching, and tuning.
• Collaborate with systems engineers to deploy models on heterogeneous GPUs.
• Lead deployment workflows, validation, rollout safety, and observability.
• Mentor engineers and raise production ML practices.

Skills

Python

PyTorch

TensorFlow

ML systems

Distributed systems

GPU optimization

Education

MS in CS/ML

Tools

SGLang

TensorRT-LLM

vLLM

ONNX Runtime

llama.cpp

Job description

Cloudflare is seeking an experienced ML Engineer to define and optimize how machine learning models run across Cloudflare’s global network. You will work with ML researchers, systems engineers, and hardware partners to bring models to production with low latency and high reliability.

You will focus on benchmarking, inference optimization, and building tooling that enables Cloudflare and its customers to ship AI applications at internet scale.