Machine Learning Engineer – Deep Learning for HFT
Core
Develop and deploy deep learning models for high-frequency trading and market making using raw tick-level order-book data.
Role type
Senior IC machine learning engineer (deep learning for HFT)
Builds
Deep learning models integrated into a live C++ trading platform
Domain
Quantitative finance / High-frequency trading
Deliverable
production ML models
Required skills
Deep learning model training, PyTorch, JAX, C++, CUDA, GPU computing, distributed training, time-series modeling, sequence modeling, experimental design, statistical analysis
Preferred skills
Order-book and market microstructure experience, latency-constrained inference optimization, custom CUDA/Triton kernels, prior trading experience
Technologies
PyTorch, JAX, C++, CUDA, Triton, GPU clusters
Responsibilities
Research and train deep learning models on large-scale order-book data to predict short-horizon market behavior; Develop sequence and time-series models for noisy financial data; Own data preparation, feature construction, and training pipelines; Evaluate models using time-aware out-of-sample validation; Improve training efficiency via distributed training and performance optimization; Integrate models into a latency-constrained C++ market-making system; Evaluate production model behavior and guide further research based on live feedback