Remote Model Optimization Engineer - AI Systems & GPU

Triwill Group; United States; Remote; USD 150,000 - 175,000; Full time

Job summary

Bright Vision Technologies is seeking a Model Optimization Engineer to maximize throughput, minimize latency, and cut costs across large neural network workloads for training and inference. You will work from low-level kernel optimization to distributed system tuning, requiring deep GPU, memory, and compiler expertise.

The role emphasizes collaboration with cross-functional partners and mentoring others, with a track record of shipping production-ready optimizations and data-driven decisions.

Qualifications

• Bachelor’s or Master’s degree in CS, CE, or related field.
• Six+ 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.
• Excellent measurement, debugging, and analytical reasoning skills.

Responsibilities

• Optimize throughput and latency for training and inference of large neural networks.
• Reduce cost across AI workloads from kernel to distributed system level.
• Collaborate with product, design, engineering, operations and business teams.
• Mentor junior engineers and contribute to code/design reviews.

Skills

Python

C++

GPU optimization

Profiling tools

Distributed training

Model compression

Memory systems

Performance engineering

Education

Bachelor’s or Master’s degree in Computer Science / Computer Engineering

Tools

Triton

CUTLASS

TensorRT

DeepSpeed

Job description

Bright Vision Technologies is seeking a Model Optimization Engineer to maximize throughput, minimize latency, and cut costs across large neural network workloads for training and inference. You will work from low-level kernel optimization to distributed system tuning, requiring deep GPU, memory, and compiler expertise.

The role emphasizes collaboration with cross-functional partners and mentoring others, with a track record of shipping production-ready optimizations and data-driven decisions.