Machine Learning Engineer – Functional Modeling, AI for Drug Discovery

Programming.com is seeking a Machine Learning Engineer to support AI-driven drug discovery initiatives in computational sciences. The role develops data pipelines, machine learning models and prototypes, and evaluation tools, while collaborating with ML architects, data engineers, and biological scientists.

Responsibilities:

• Data Engineering and Pipeline Development: Build and maintain interim data pipelines using Python, Pandas, and SQL to clean, transform, integrate, and structure complex datasets for machine learning applications
• Machine Learning Model Development: Develop, train, tune, and evaluate statistical baseline models using Scikit-learn and create advanced graph-based modeling prototypes across multiple biological pilot projects
• Rapid Prototyping: Translate ML architectural guidance into functional proofs of concept, delivering initial solutions within 3–4 months while prioritizing high-impact outcomes
• ML Codebase Development: Organize, package, and document machine learning code to make model execution and evaluation accessible to biological scientists and other non-ML stakeholders
• Model Evaluation and Validation: Develop standardized evaluation workflows and tools to support model performance assessment, hypothesis validation, and rapid experimentation
• Cross-Functional Collaboration: Partner with data engineering teams to develop scalable, long-term data workflows and ensure effective integration of ML models with data infrastructure
• Stakeholder Communication: Communicate technical findings, limitations, and implementation approaches clearly to ML architects, data engineers, and biological domain experts
• Continuous Improvement: Incorporate feedback from experimental partners and stakeholders to refine models, pipelines, and evaluation tools

Requirements:

• At least 3+ years of hands-on Machine Learning Engineering experience ; candidates with equivalent practical experience and 5+ years of building and deploying end-to-end ML pipelines will also be considered
• Strong programming skills in Python, Pandas, and SQL for data processing, transformation, and pipeline development
• Proven experience developing and evaluating applied machine learning models using Scikit-learn or comparable ML frameworks
• Experience cleaning, integrating, and restructuring complex or unstructured datasets into ML-ready formats
• Strong understanding of data organization and schema design to support effective machine learning workflows
• Experience translating real-world scientific or business problems into practical machine learning solutions
• Ability to develop maintainable, reusable, and well-documented code for use by technical and non-technical stakeholders
• Excellent communication, collaboration, and problem-solving skills
• Ability to work independently in a dynamic, exploratory environment and deliver results within tight timelines
• Master's degree or Ph.D. in Computer Science, Bioinformatics, Machine Learning, Computational Biology, or a related field is preferred
• Experience with deep learning frameworks such as PyTorch
• Familiarity with PyTorch Geometric or other graph machine learning frameworks
• Experience developing graph-based models, statistical baselines, or advanced ML prototypes
• Background in AI for Drug Discovery (AIDD), computational biology, bioinformatics, antibody discovery, or biological data analysis
• Experience collaborating with biologists, bench scientists, or scientific research teams
• Familiarity with AI-assisted development tools or agentic AI systems
• Experience building reproducible ML workflows, model evaluation utilities, and tools for non-ML users