About the Role We are seeking an AI Engineer with a strong AI4Science background to design, develop, and deploy machine learning systems for scientific discovery. This role sits at the intersection of deep learning, high-performance computing, and scientific domains such as materials science and genomics. You will work closely with researchers and engineers to build scalable ML pipelines, manage GPU-accelerated infrastructure, and train state-of-the-art models for scientific applications. Key Responsibilities AI & Machine Learning . Design, train, and optimize deep learning models using PyTorch, TensorFlow, and/or JAX . Implement scalable training workflows for large scientific datasets . Apply ML methods to materials science, genomics, or other scientific domains . Evaluate model performance and ensure reproducibility of results Scientific Computing & AI4Science . Work with scientific ML and simulation tools such as PyMatGen, ASE, DFT workflows, AlphaGenome, Plink, QUANTO, or related libraries . Integrate ML models with physics-based or data-driven scientific pipelines . Collaborate with domain scientists to translate scientific problems into ML solutions Systems & Infrastructure . Administer and maintain Ubuntu Linux environments for AI workloads . Manage CUDA drivers and CUDA toolkit installations for GPU-accelerated training . Develop and maintain Bash shell scripts for automation and system workflows . Create and manage Python virtual environments (venv, conda, poetry, etc.) DevOps & MLOps . Manage git repositories, branching strategies, and collaborative workflows . Build, deploy, and maintain Docker containers for reproducible ML environments . Support experiment tracking, versioning, and model reproducibility . Assist with scaling workloads on local clusters or cloud infrastructure (if applicable)
