Bridge the gap between research and production by building scalable machine learning pipelines and optimizing model inference engines.
Responsibilities
- Optimize inference engines for sub-millisecond execution
- Collaborate with researchers to deploy NLP and Computer Vision models for alternative data
- Monitor model drift and automate retraining pipelines
Requirements
- Experience with PyTorch, TensorFlow, or JAX
- Strong background in C++ and Python
- Experience deploying ML models in latency-critical environments
- Knowledge of CUDA and GPU optimization is a strong plus