Machine Learning Engineer (on-site)

OPSWAT, a global leader in IT, OT, and ICS critical infrastructure cybersecurity, delivers an end-to-end platform that gives public and private sector organizations and enterprises the critical advantage needed to protect their complex networks, secure their devices, and ensure compliance. Over the last 20 years our commitment to innovative technology has earned the trust of more than 1,700 organizations, governments, and institutions globally, solidifying our role in protecting the world’s critical infrastructure and securing our way of life.

What You Will Be Doing

• Turn detection problems into well-posed ML problems with a clear hypothesis, baseline, and success criteria

• Build, label, and version the datasets used for training and evaluation

• Design, train, and tune models; analyze their errors and feed the findings back into data, features, or architecture

• Define evaluation protocols: metrics, splits, held-out test sets, and thresholds tied to product constraints such as false-positive rate and latency

• Take models from experiment to production on AWS together with MLOps and software engineers, including packaging and inference optimization

• Monitor deployed models for drift and drive retraining when needed

• Keep experiments reproducible and documented, and present results and trade-offs to engineering and product

What We Need From You

• 3+ years of hands-on experience as a Machine Learning Engineer, Data Scientist, or Applied Scientist, with models delivered to production

• Bachelor’s or Master’s degree in Computer Science, Mathematics, Statistics, or a related field

• Strong Python and the scientific stack (NumPy, pandas, scikit-learn, PyTorch or TensorFlow)

• Solid grounding in statistics and ML fundamentals: bias/variance, class imbalance, leakage, calibration

• Practical experience with AWS for data storage and training workloads

• Clear written and spoken English

Nice to Have

• Experience with experiment tracking and model registries (MLflow, Weights & Biases, or similar)

• Experience optimizing and packaging models for inference (quantization, distillation, ONNX, Docker)

• Knowledge of file formats and binary analysis

• Background in cybersecurity, threat detection, or another adversarial domain

• Publications, open-source contributions, or a competitive ML track record