ML Performance Engineer – Build Scalable Training Pipelines

Fintal Partners; New York (NY); On-site; USD 180,000 - 280,000; Full time

Benefits offered by this job

401(k) match up to 50%

Health, dental, vision, life

Mental health coverage

25 days paid leave

Office perks & events

Job summary

Fintal Partners seeks a Machine Learning Performance Engineer to shape the flagship AI program. You will optimize training and inference pipelines, explore framework internals, and hunt bottlenecks while collaborating with researchers and engineers across global teams.

The role offers exposure to high-performance ML in a global trading context, with competitive compensation, health coverage, and generous leave.

Qualifications

• Strong low-level GPU programming with CUDA.
• Deep familiarity with ML frameworks (PyTorch, JAX, TensorFlow).
• Solid grounding in computer architecture and parallelism.
• Experience with C++ and Python for ML infra.
• Experience with large-scale distributed training and OSS contributions.

Responsibilities

• Build robust, scalable training and inference pipelines for deep learning.
• Work inside the internals of open-source deep learning frameworks and extend functionality.
• Identify and remove performance bottlenecks in ML pipelines.
• Collaborate with researchers and engineers across teams.
• Develop deep knowledge of trading systems and their ML components.

Skills

CUDA programming

PyTorch / JAX / TensorFlow

C++

Python

computer architecture

distributed training

open-source contributions

Tools

PyTorch/JAX/TensorFlow

XLA/Flax

Job description

Fintal Partners seeks a Machine Learning Performance Engineer to shape the flagship AI program. You will optimize training and inference pipelines, explore framework internals, and hunt bottlenecks while collaborating with researchers and engineers across global teams.

The role offers exposure to high-performance ML in a global trading context, with competitive compensation, health coverage, and generous leave.