Senior Machine Learning Software Engineer, Aqemia

• 6+ years of experience in software engineering with strong focus on machine learning systems
• Deep proficiency in Python and ML ecosystem (e.g. PyTorch, scikit-learn, MLFlow)
• Solid understanding of data and model lifecycle management, versioning, and deployment
• Experience building ML infrastructure and model-serving pipelines in production environments
• Familiarity with cloud-based architecture (AWS preferred), containerization (Docker), and orchestration tools
• Ability to work autonomously and lead initiatives with high technical ownership
• Strong communication skills and ability to work closely with scientists and engineers alike

Desirable

• As a Senior ML Software Engineer in the DH Team, you will focus on building and scaling the platform-facing product that manages the full lifecycle of Aqemia’s predictive models, our core scientific assets
• You’ll scale and industrialize ML/deep learning models developed by research scientists, so they can be efficiently served to our Drug Hunter community
• You will play a critical role in the development, deployment, and maintenance of single predictors, ensuring they are robust, reproducible, and seamlessly integrated into the platform that drives our drug discovery engine
• This role is deeply technical and foundational to our platform’s performance, reliability, and scalability
• Design and implement ML product and infrastructure to support the training, evaluation, deployment, and versioning of predictive modelsIndustrialize and optimize ML/deep learning models developed by scientists, making them scalable and cost-efficient in production
• Collaborate closely with scientists to integrate diverse predictors (physics-based, AI-based, hybrid) into the platform
• Ensure reproducibility, traceability, and performance of model pipelines across the full lifecycle
• Develop APIs and tools that expose predictors as scalable services to other teams
• Contribute to software engineering best practices across the ML stack (testing, CI/CD, observability)
• Partner with platform engineers and product stakeholders to ensure technical alignment and delivery