AI Performance Engineer
$100,000–$150,000 year
RemoteUnited States
Job Summary
Profile and optimize end-to-end AI training and inference pipelines for throughput, latency, and cost. Identify bottlenecks across data loading, model compute, communication, and memory, then implement quantization, sparsity, and pruning strategies to reduce model footprints. Tune distributed training with tensor parallelism, FSDP, and ZeRO-style sharding, while optimizing attention implementations and KV cache management for LLM serving. Drive compiler-level optimizations using Triton, XLA, and TorchInductor to achieve measurable performance gains. Build rigorous benchmark suites, collaborate with ML teams to embed best practices, and document tuning playbooks. Stay current with AI systems research to translate advances into production improvements.
Required Qualifications
- Bachelor's or Master's degree in Computer Science, Computer Engineering, or a related field.
- Six or more years of experience in performance engineering, ML systems, or HPC.
- Strong proficiency in Python and C++.
- Hands-on experience optimizing deep learning workloads on modern GPUs.
- Deep understanding of distributed training and inference techniques.
- Experience with profiling tools across CPU, GPU, and distributed systems.
- Familiarity with model compression techniques and their accuracy implications.
- Strong grasp of memory hierarchies, communication primitives, and parallelism strategies.
- Excellent measurement, debugging, and analytical reasoning skills.
- Strong communication and collaboration skills.
Desired Qualifications
- Experience optimizing LLM inference at production scale.
- Contributions to vLLM, TensorRT-LLM, DeepSpeed, or similar projects.
- Familiarity with custom kernel authoring in Triton or CUTLASS.
- Experience with FinOps for AI workloads.
- Publications or talks on AI systems performance.
Hiring someone like this?
Get your role in front of qualified candidates on Sorce.