Applied Deep Learning Scientist, Geometric Deep Learning - Drug Discovery AI

Find out exactly what skills, experience, and qualifications you will need to succeed in this role before applying below.

NVIDIA is using the power of high performance computing and AI to accelerate digital chemistry, biology and atomistic modeling! We are seeking passionate and hardworking individuals to help us realize our mission.

As an Applied Deep Learning Scientist, Geometric Deep Learning, you will join a research and development team passionate about infrastructure development and collaborations with industry and academic partners.

This position provides the opportunity to research, implement, productize, and deliver deep learning algorithms for applications to atomistic modeling.

The team engages in applied research and then helps productize this work.

What you will be doing :

• Prototype and build deep learning algorithms for graph and geometric deep learning in atomistic modeling.
• Design metrics for and assist with the evaluation of model predictions and results.
• Know the latest research and identify ways to capitalize on new advancements, either as applied research projects or by directly integrating into product development.
• Collaborate with multiple AI infrastructure and research teams.
• Find opportunities to incorporate advances in the field and other NVIDIA products into our infrastructure.

What we need to see :

• 5+ years of proven experience.
• PhD Degree in a quantitative field such as Statistics, Physics, Computational Biology, Quantum Chemistry, Computer Science, Mathematics (or a related field), or equivalent experience.
• Expertise in deep learning and machine learning in atomistic modeling or related applications with geometric learning tasks.
• Strong experience with Python and deep learning frameworks (PyTorch, TensorFlow, Jax, Warp) and relevant specialized deep learning libraries (e.g. PyG, DGL, e3nn).
• Experience with modeling biological, chemical or material science systems, such as small molecules, proteins, solids, surfaces and experience with related modeling and simulation tools.
• Recognition for technical leadership contributions, deep understanding of the fundamentals, capable of self-direction, and willingness to learn from and teach others.
• You should display strong communication skills, be organized and self-motivated, and play well with others (be an excellent teammate).

Ways to stand out from the crowd :

• Familiarity with latest advances in geometric and / or generative atomistic deep learning models in biological sciences, such as DiffDock, or similar equivariant models from other application areas.
• Experience with protein or small molecule simulation tools that use atomistic or coarse grained interaction models such as OpenMM, GROMACS, LAMMPS.
• Background with ML model design for atomistic systems and with infrastructure building for model design, deployment or data generation stages (e.

g. active learning frameworks).

• Experience with C / C++, CUDA, docker.
• Experience with open source development.
• Relevant publication history and / or conference attendance.

The base salary range is $156,000 - $287,500. Your base salary will be determined based on your location, experience, and the pay of employees in similar positions.

You will also be eligible for equity and benefits.

NVIDIA is committed to fostering a diverse work environment and proud to be an equal opportunity employer. As we highly value diversity in our current and future employees, we do not discriminate (including in our hiring and promotion practices) on the basis of race, religion, color, national origin, gender, gender expression, sexual orientation, age, marital status, veteran status, disability status or any other characteristic protected by law.

J-18808-Ljbffr