Senior ML Engineer: Real-Time Inference & GPU Pipelines

Fintal Partners; New York (NY); On-site; USD 150,000 - 230,000; Full time

Job summary

Fintal Partners is seeking a Machine Learning Engineer to build and optimize large-scale ML training and inference systems across our trading ecosystem. You will collaborate with researchers and engineers to leverage GPU acceleration, distributed computing, and open-source tools, driving real-time predictions and scalable ML workflows.

You will contribute to the design of model frameworks capable of handling high-volume trading data and will work with HPC specialists to minimize training times

Qualifications

• 5+ years of experience in machine learning for training or inference systems.
• Experience with real-time, low-latency ML pipelines in high-performance environments is a strong plus.
• Strong engineering skills, including Python, CUDA, or C++.
• Knowledge of machine learning frameworks such as PyTorch, TensorFlow, or JAX.

Responsibilities

• Develop large-scale distributed training pipelines to manage datasets and complex models
• Build and optimize low-latency inference pipelines, ensuring models deliver real-time predictions in production systems
• Develop libraries to improve the performance of machine learning frameworks
• Maximize performance in training and inference using GPU hardware and acceleration libraries
• Design scalable model frameworks capable of handling high-volume trading data and delivering realtime, high-accuracy predictions
• Collaborate with quantitative researchers to automate ML experiments, hyperparameter tuning, and model retraining
• Partner with HPC specialists to optimize workflows, improve training speed, and reduce costs
• Evaluate and roll out third-party tools to enhance model development, training, and inference
• capabilities
• Dig into the internals of open-source ML tools to extend their capabilities and improve performance

Skills

Python

CUDA

C++

PyTorch

TensorFlow

JAX

GPU programming

Distributed training

Real-time inference

Horovod

NCCL

Tools

CuDNN

TensorRT

Horovod

NCCL

Job description

Fintal Partners is seeking a Machine Learning Engineer to build and optimize large-scale ML training and inference systems across our trading ecosystem. You will collaborate with researchers and engineers to leverage GPU acceleration, distributed computing, and open-source tools, driving real-time predictions and scalable ML workflows.

You will contribute to the design of model frameworks capable of handling high-volume trading data and will work with HPC specialists to minimize training times