ML Performance Engineer: Scale GPU-Driven Training

Decisive Point; Sunnyvale (CA); On-site; USD 180,000 - 240,000; Full time

Job summary

Applied Intuition, Inc. is a Silicon Valley leader powering the future of physical AI. We seek a Performance Engineer to optimize large-scale ML workloads, focusing on distributed training, batch inference, and cost-effective data processing.

You will own profiling across the stack, identify where compute and wall-clock time are spent, and drive improvements that speed time-to-result and reduce processing costs. Join a team that values collaboration and technical excellence.

Qualifications

• Hands-on ML performance engineering experience with profiling and roofline analysis.
• Experience with distributed multi-node training at scale and diagnosing scaling inefficiency.
• Deep familiarity with GPU/accelerator performance concepts including memory bandwidth and kernel launch overhead.
• Experience with high-throughput or batch inference systems (Triton, TensorRT, ONNX Runtime, Ray).
• Fluency in Python and proficiency in C++ or another systems language.
• Excellent debugging, analytical and problem-solving skills.
• A deep understanding of machine learning foundations and the ability to develop solutions without a playbook.

Responsibilities

• Profile and optimize distributed training end to end including data loading, preprocessing, and gradient communication.
• Optimize large-scale offline and batch inference over petabyte-scale logs.
• Establish roofline and performance models and prioritize optimization opportunities.
• Improve multi-node scaling efficiency with sharding, parallelism, and communication strategies.
• Drive cluster goodput by reducing GPU idle time due to data pipelines and I/O bottlenecks.
• Build benchmarking, observability, and regression-detection tooling for evolving models.
• Collaborate with engineers across functions to solve large-scale data and compute problems.

Skills

ML performance engineering

Distributed multi-node training

GPU/accelerator concepts

Python

C++

Debugging

Problem solving

ML foundations

Tools

NVIDIA Triton Inference Server

TensorRT

ONNX Runtime

Ray

NCCL

Job description

Applied Intuition, Inc. is a Silicon Valley leader powering the future of physical AI. We seek a Performance Engineer to optimize large-scale ML workloads, focusing on distributed training, batch inference, and cost-effective data processing.

You will own profiling across the stack, identify where compute and wall-clock time are spent, and drive improvements that speed time-to-result and reduce processing costs. Join a team that values collaboration and technical excellence.