2023 Computational Scientist in Machine/Deep Learning Intern

Key Skills

Deep Learning, Machine learning techniques, Neural Networks, Python Programming, PyTorch, Reinforcement Learning, TensorFlow, Transformer

Job Description

The Future Talent Program features internships that lasts up to 12 weeks and will include one or more projects. These opportunities in our Research & Development Division can provide you with great development and a chance to see if we are the right company for your long-term goals.

Emerging advanced deep learning models have demonstrated great potential in synthesizing information from multiple sources to guide decision-making and optimize resources allocation in early discovery and preclinical study. Our company has a long history of investing in cutting edge machine learning models, with pioneered work in developing widely used public R package for random forest and internal machine learning MIX QSAR infrastructure. ML-based QSAR models are broadly adopted for rolling human dose prediction in Preclinical Development (PCD) ADME’s newly built tool Automated Dose Prediction (ADP), with the purpose of improving efficiency and capability of human dose prediction to streamline medicinal compound discovery throughout ROP.

While in-silico QSAR models are being updated quarterly, ADME PIs continue to notice a frustrating discrepancy between experimental measurements and QSAR predictions for animals and human cell models, with an interesting observation that measured animal data better characterize new animal species and human cell models than QSAR models do in many programs. This discrepancy and observation point to a great opportunity of improving accuracy of predictive models for translational study in preclinical stage. With the release of scientific data consumption platform (SDCP), we are now able to access all in-vitro and in-vivo data from decades of PCD research. Building new advanced deep learning based predictive models from in-silico, in-vitro, and in-vivo data for translational study has immediate impact in improving human dose prediction accuracy and, furthermore, enables the acceleration of early discovery.

The intern will be expected to experiment with advanced deep learning methods on multiple different predictive tasks closely tied to PCD research and packaged up developed models to work as foundational building blocks for future PCD data science products.

Primary Objectives:

• Gather and clean data from SDCP for each task.
• Explore internal and external software and platforms to develop a cloud-based (AWS or Databricks) model development platform.
• Dive deep into new deep learning methods published in recent years and carry out experiments on multiple tasks.
• Study domain applicability of new models and characterize model performance by comparing with current models.

Benefits to the Group:

• Foundational building block for data science products in PCD and across Discovery, Preclinical, and Translational Medicine(DPTM).
• Improve dose prediction accuracy in early discovery and PCD stages.
• A cloud-based model development platform for PCD modelers.
• More trustworthy predictions for in-vitro and in-vivo assays.

Benefits for the Intern:

• Opportunity to dive deep into modern deep learning technologies, including but not limited to, graphical neural network, reinforcement learning, and bidirectional transformer.
• Hands on experience on learning, adapting, refining, and developing predictive models with real applications in medicinal chemistry discovery and preclinical study.
• Work daily in a diverse team across our Research & Development Division on ground-breaking technologies, gaining deeper exposure to drug development.
• Potential for a publication.

Required Education & Experience:

• Candidates must be PhD students conducting machine learning related computational research.
• Candidates must be proficient in Python programming and machine learning packages, e.g., PyTorch, Tensorflow.
• Candidates must have a passion in drug R&D.
• Candidates must be available to work full-time for 12 weeks beginning on 5JUN23

We are a research-driven biopharmaceutical company. Our mission is built on the simple premise that if we “follow the science” that great medicines can make a significant impact to our world. We believe that a research-driven enterprise dedicated to world-class science can succeed by inventing medicine and vaccine innovations that make a difference for patients across the globe. 

Who we are …

We are known as Merck & Co., Inc., Rahway, New Jersey, USA in the United States and Canada and MSD everywhere else. For more than a century, we have been inventing for life, bringing forward medicines and vaccines for many of the world's most challenging diseases. Today, our company continues to be at the forefront of research to deliver innovative health solutions and advance the prevention and treatment of diseases that threaten people and animals around the world.

What we look for …

Imagine getting up in the morning for a job as important as helping to save and improve lives around the world. Here, you have that opportunity. You can put your empathy, creativity, digital mastery, or scientific genius to work in collaboration with a diverse group of colleagues who pursue and bring hope to countless people who are battling some of the most challenging diseases of our time. Our team is constantly evolving, so if you are among the intellectually curious, join us—and start making your impact today.