ML Engineer

Impressit is looking for an MLOps Software Engineer to join a cross-functional team building the infrastructure behind autonomous AI trading systems, as part of a larger trading division. This is a great opportunity to contribute to a meaningful product with real-world impact, while working with modern technologies and international teams.

— Own MLOps end-to-end — from model training and evaluation to trading evaluation
— Develop large-scale deployment of GPU nodes running across dozens of Kubernetes clusters across regions, using CUDA, Python, PyTorch, Triton, Redis, NCCL, NVLink
— Build simulation pipelines to scale hyperparameter testing for model training and trading, synchronizing model parameters with financial trading parameters
— Automate feature evaluation and experimentation for model training
— Automate model training and performance evaluation
— Combine classical model evaluation with financial trading metrics — Sharpe, Turnover, Fitness, Returns, Drawdown, Margin, Long/Short Count, Sector/Subindustry Allocations, etc.
— Build, maintain, and enhance model pipelines using MLOps and AIOps frameworks
— Work across the full data and model infrastructure stack, including SageMaker Studio
— Partner with Data Scientists to set up model monitoring and feedback systems
— Be part of a sub-team focused on fully autonomous AI trading within a larger trading division

— Bachelor's degree or above; a Software Engineering background is preferred
— Hands-on experience with CUDA and PyTorch
— Strong knowledge of low-level languages such as C++ or Go
— Experience with at least one of the following: high-scale distributed training and inference/ML systems; parallel and distributed computing with multiple GPUs; high-throughput scheduling as a service at supercomputing scale; or the ability to resolve Segmentation Faults
— Proven experience with Unit Tests, Integration Tests, and error handling to keep trading systems fault-tolerant and robust
— Experience with orchestration tools — DAGs in Airflow or Prefect, MLflow
— Experience with deployment — Docker, AWS, load testing
— Good communicator, comfortable working in cross-functional teams
— Good to have: broad knowledge of network technologies, inside and out

— Broad, in-depth understanding of network technologies
— Prior experience in fintech / algorithmic trading
— Passion for clean code, developer experience, and end-user quality