Senior Data Scientist

Role & responsibilities

• Develop, design, and implement advanced algorithms for extracting structured information from unstructured text data. Also, should be able to solve problem statements having low labeled information.
• Extract conclusive information from extensive datasets to discover new relationships within medical, biological, and life sciences domains.
• Make predictions to assist healthcare practitioners to boost the success rates of clinical trials.
• Collaborate with cross-functional teams, including data scientists, software engineers, technology architects, and experts in GPU systems.
• Conduct up-to-date and state-of-the-art advanced data analytics on acquired digital data, both using standard statistics and contemporary machine learning approaches.
• Stay up on the state of the art in healthcare and life science to apply the latest advancements in the field to customer needs.
• You will bring your curious, innovative, and collaborative mindset to make the best use of the biomedical domain data generated within our department and use state-of-the-art machine learning (ML) methods and statistical techniques to accelerate drug design.
• Develop new algorithms, methods, and implement ML models to predict compound properties.
• Apply ML data processing to understand relationships between structure and molecular properties.
• Investigate new algorithms or modeling strategies, identify research articles, and reproduce/apply innovative methodology to generate insights related to discovery data.
• Quickly learn and pilot the use of tools, data sources and analytical techniques needed to answer a wide range of critical business questions.
• In collaboration with cross-functional partners, provide scientific and strategic input to support discovery and lead optimization activities.

• Deliver clear and concise presentations for audiences with different expertise.

Preferred candidate profile

1. 4 to 7 years of relevant experience (5 to 8 years if holding a bachelor's degree).
2. At least 4+ years of work-related experience in software development, deep learning, machine learning, NLP/LLM or high-performance computing.
3. Competency in at least one programming language (Python preferred or similar).
4. Experience with software development & modern Deep Learning software architecture and frameworks like Scikit-learn, Keras, Pytorch, TensorFlow and/or CUDA.
5. Experience with reproducible data science tools and practices. Previous research experience either in academia or industry.
6. Must enjoy interacting with forward-thinking people, life-long learning, and staying at the cutting-edge of the domain.
7. Familiarity with collaboration tools and environments (e.g. OKRs, Jupyter notebooks, git, Jira, Docker, etc.)
8. Significant machine / deep learning experience with healthcare data and published record of thought leadership in a technical area or industry segment.
9. Experience in the application of data science methods to drug discovery. Having experience of working on at least one dataset from clinical trials, indication expansion and prioritization, target identification, biomarkers, ADCs,, PROTACs, drug combinations, drug repurposing/reformulation, antibody engineering, SAR - De Novo, life sciences ontology/ knowledge graphs or related fields.
10. Experience with generative algorithms and explainable AI. Expertise in ADME/PD/PK is a plus.
11. Proven experience working on or creating working ML/DL models for medical, biological, and life sciences datasets (minimum of 2 major projects).
12. Expertise in healthcare or life science and the processing of healthcare data.
13. Understanding of how to apply deep learning or machine learning into the healthcare process. Demonstrated experience of optimization workloads with GPU technology.
14. Sound knowledge of probability theory or statistics is a definite plus.