Remote anywhere in Canada, this machine learning systems engineer benchmarks and tunes production LLM serving across AWS Trainium2 and Trainium3. Python and PyTorch skills are central.

Capgemini Engineering seeks a hands-on engineer focused on accelerator performance and customer-ready inference systems. You will compare Trainium with leading GPUs, measure latency-throughput frontiers, and optimize price-performance under representative loads. The work includes Qwen-family models, vLLM, AWS Neuron, long contexts, and multi-chip serving.

Key Responsibilities

Benchmark workloads across Trainium generations and leading GPUs

Control prompts, concurrency, cache state, and warm-up

Deliver reproducible price-performance comparisons aligned with service objectives





Apply architecture-specific optimizations to long-context workloads

Support workshops enabling independent operation and tuning

Requirements

Five-plus years of machine learning or systems engineering experience

Production inference or serving experience for two-plus years

Hands-on AWS Trainium, Inferentia, or AWS Neuron experience preferred

Experience profiling accelerator workloads at framework, compiler, or kernel level

Robust written and verbal communication for technical audiences

Bring rigorous performance experimentation and accelerator migration expertise to AWS Trainium inference engineering at Capgemini Engineering.

📌 AWS Trainium LLM Systems Engineer (Winnipeg)
🏢 Capgemini Engineering
📍 Winnipeg