AI Performance Engineer

About this role

Responsibilities

• Profile and optimize end-to-end AI training and inference pipelines for throughput and latency.
• Implement quantization, sparsity, and pruning strategies to reduce model footprint.
• Tune distributed training using tensor parallelism and ZeRO-style sharding techniques.
• Build rigorous benchmark suites and regression frameworks for workload validation.
• Collaborate with ML teams to embed performance best practices into standard pipelines.