Key Responsibilities:
- Design and train advanced machine learning models for drug discovery, including deep learning and graph-based architectures.
- Own end-to-end model lifecycle from problem definition to production deployment and continuous improvement.
- Conduct rigorous benchmarking, validation, and performance evaluation against scientific and business objectives.
- Deploy scalable, reliable model inference services meeting latency, throughput, and cost requirements.
- Build automated training, retraining, and monitoring pipelines including model drift detection.
- Optimize models and pipelines for performance, reliability, and scalability across production environments.
- Establish and promote engineering best practices for reproducibility, testing, and deployment standards.
- Collaborate with cross-functional teams to translate research innovations into production-ready AI solutions.
- Partner with scientific experts to validate models against biological and chemical benchmarks.
- Mentor teams and contribute to raising engineering excellence across the AI for Research organization.
Essential Requirements:
- Minimum four years of experience building, training, and deploying machine learning models with measurable real-world impact.
- Deep proficiency in Python and frameworks such as PyTorch or JAX; expertise in model design and optimization.
- Proven experience fine-tuning and deploying large pre-trained and foundation models, including language and scientific models.
- Strong understanding of model evaluation (benchmarking, cross-validation, and performance across data distributions).
- Experience with distributed training and large-scale computing environments for high-performance training.
- Hands-on expertise optimizing models/pipelines for latency, throughput, cost, and production performance.
- Experience with MLOps (experiment tracking, model versioning, reproducibility, and cloud deployment).
- Strong problem-solving, collaboration, and communication skills.