GPU-Optimized ML Inference Engineer

Goliath Partners Inc.; New York (NY); On-site; USD 200,000 - 300,000; Full time

Benefits offered by this job

Discretionary bonus

Job summary

Goliath Partners Inc. (New York) is seeking a Machine Learning Performance Engineer to accelerate production inference by writing and tuning GPU kernels, identifying bottlenecks, and optimizing models for low latency deployment.

The role collaborates with ML researchers, computing infrastructure, and hardware acceleration teams, focusing on fast, reliable inference for trading workloads. The ideal candidate has 2+ years of production inference performance improvement, strong Python and C++, and

Qualifications

• 2+ years improving deep learning inference performance in production
• Ability to write and tune GPU kernels for production inference
• Experience with memory access patterns and hardware communication for performance

Responsibilities

• Write and tune GPU kernels to accelerate production inference
• Investigate performance bottlenecks from memory access to inter-component communication
• Reduce model size and compute while preserving numerical stability
• Compare hardware options to optimize deployment for demanding workloads
• Partner with researchers and engineering teams to bring optimized models into production
• Profile systems and compare performance across hardware architectures

Skills

Python

C++

GPU programming

Performance profiling

Low latency

Numerical stability

Tools

PyTorch

JAX

CUDA

Job description

Goliath Partners Inc. (New York) is seeking a Machine Learning Performance Engineer to accelerate production inference by writing and tuning GPU kernels, identifying bottlenecks, and optimizing models for low latency deployment.

The role collaborates with ML researchers, computing infrastructure, and hardware acceleration teams, focusing on fast, reliable inference for trading workloads. The ideal candidate has 2+ years of production inference performance improvement, strong Python and C++, and