Machine Learning Engineer

About mlHealth 360 mlHealth 360 is a Health-Tech company dedicated to revolutionizing healthcare through deep learning-powered medical image screening. We empower healthcare professionals and institutions with innovative AI tools to improve patient outcomes, reduce costs, and enhance efficiency. Our focus is on developing state-of-the-art models (CNNs, Transformers, LLMs, and VLMs) for automated diagnosis, segmentation, and clinical decision support.

Role Description As an ML Engineer at mlHealth 360, you will be a hands-on technical leader, driving the end-to-end development of AI-powered diagnostic tools. This role requires expertise in research-grade deep learning and production-grade MLOps to deploy scalable, high-performance models in clinical settings. You will bridge R&D experimentation and engineering execution, ensuring models are clinically robust, efficient, and integrated into real-world workflows.

Key Responsibilities 1. Deep Learning Model Development • Design, implement, and train advanced architectures (U-Net, CNN, ViT, 3D CNNs/Transformers, VLM, LLM) for segmentation, Report Generation, detection, classification, and multi-modal analysis in medical imaging. • Implement and adapt state-of-the-art algorithms and model architectures based on cutting-edge research papers. • Apply self-supervised learning (e.g., contrastive learning), reinforcement learning (RL), and diffusion models for robust and adaptive solutions. • Optimize models for high accuracy, low latency, and clinical interpretability using techniques like LoRA, adapter tuning, attention mechanisms, and multi-modal fusion (imaging + clinical text/EHRs). • Develop solutions for 3D volumetric data (CT, MRI) and real-world clinical deployment. 2. End-to-End Data Pipelines • Build and maintain scalable pipelines for ingesting, preprocessing, and versioning DICOM/NIfTI datasets (CT, MRI, X-ray). • Automate data augmentation, normalization, and annotation using tools like Encord, MONAI, and OpenCV. • Ensure data privacy and compliance with HIPAA/GDPR standards. 3.

MLOps & Deployment • Containerize models using Docker and deploy them on Kubernetes for scalable, low-latency inference in clinical environments. • Implement MLOps best practices: automated testing, model monitoring, continuous training (CT) loops, and A/B testing. • Optimize models for edge deployment (quantization, pruning, ONNX/TensorRT acceleration). 4. Research & Innovation • Stay updated with SOTA research in medical imaging (e.g., foundation models, diffusion models) and prototype novel solutions. • Publish findings in conferences/journals and contribute to open-source projects. Required Experience • 2+ years of hands-on experience in building and deploying ML models, with a focus on medical imaging or computer vision. • 1+ year of experience in medical image analysis (CT, MRI, X-ray) and radiological workflows. • Proficiency in: o Deep Learning Frameworks: PyTorch, TensorFlow. o Medical Imaging Libraries: MONAI, ITK, SimpleITK, pydicom. o Annotation Tools: Encord, Labelbox, CVAT. o MLOps & Cloud Platforms: AWS, Azure, Databricks, Docker, MLflow, Kubernetes. o Production Deployment: Model optimization (quantization, ONNX, TensorRT), edge deployment, and scalable inference.

Education • Bachelor's, Master's in Computer Science, Biomedical Engineering, Data Science, or a related field, with a portfolio of deployed ML projects in healthcare (e.g., GitHub, research publications, or product demos). Why Join mlHealth 360? • Work on impactful AI solutions that directly improve patient care. • Collaborate with cross-functional teams (engineers, clinicians, researchers). • Access to cutting-edge tools, datasets, and research opportunities. • Growth opportunities: Mentorship, conferences, and access to cutting-edge research in medical AI.