Machine Learning Performance Engineer

Goliath Partners; 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 is partnered with an established quantitative trading firm seeking an engineer to improve the performance of machine learning models in production.

Working within its central engineering group, you’ll tackle the hardware and software challenges behind fast, reliable inference. The work combines hands-on GPU optimization with broader decisions about how and where models should run, alongside specialists in machine learning, computing infrastructure, and hardware acceleration.

They are currently looking for a Machine Learning Performance Engineer based in New York.

• Write and tune GPU kernels to accelerate production inference
• Investigate performance bottlenecks, from memory access patterns to communication between hardware components
• Reduce model size and computational demands while preserving numerical stability
• Compare hardware options and help determine the best deployment approach for demanding trading workloads
• Partner with researchers and engineering teams to bring optimized models into production
• 2+ years improving deep learning inference performance in production environments where speed or throughput is critical
• Strong Python and C++, with experience working beneath the high-level APIs of frameworks such as PyTorch or JAX
• Practical experience developing custom GPU kernels and using inference optimization tools
• Detailed knowledge of GPU execution, memory behavior, and mixed-precision computation
• A measurement-driven approach to profiling systems and comparing performance across different hardware architectures

Preferred Skills

• Experience deploying or optimizing models on FPGAs or ASICs
• Familiarity with inference workloads where individual predictions must be delivered with exceptionally low latency

Candidates from outside financial services are welcome; trading experience is not required.

Compensation

• $200K–$300K base salary plus discretionary bonus