Remote GPU Kernel Engineer for AI/ML (PyTorch/Triton)

NLB Services; United States; On-site; USD 140,000 - 230,000; Full time

Job summary

Wipro is seeking a highly skilled GPU Kernel Developer to join our AI/ML engineering team on a remote basis. You will design, implement, and optimize GPU kernels for AI/ML workloads, with an emphasis on GEMM and high-performance tuning across GPU architectures.

Collaborate with researchers to accelerate BERT and transformer-based models, and integrate optimized kernels into PyTorch and Triton. You will conduct performance profiling, benchmarking, and tuning in production environments.

Qualifications

• Must have deep experience in GPU kernel development for AI/ML workloads.
• Hands-on work with PyTorch and Triton is required.
• Strong programming in Python, C and C++ and system-level awareness.

Responsibilities

• Design, implement, and optimize GPU kernels for AI/ML workloads.
• Focus on GEMM and other performance-critical ops across GPU architectures.
• Collaborate with researchers to accelerate BERT and transformer models.

Skills

GPU kernel development

PyTorch

Triton

Python

C/C++

BERT

GPU architectures

High-performance computing

Parallel programming

Job description

Wipro is seeking a highly skilled GPU Kernel Developer to join our AI/ML engineering team on a remote basis. You will design, implement, and optimize GPU kernels for AI/ML workloads, with an emphasis on GEMM and high-performance tuning across GPU architectures.

Collaborate with researchers to accelerate BERT and transformer-based models, and integrate optimized kernels into PyTorch and Triton. You will conduct performance profiling, benchmarking, and tuning in production environments.