Senior Computational Data Engineer

Ten
63 Therapeutics is focused on improving human health by developing better, more durable therapeutics against cancer and some of the world's most lethal diseases. We are leveraging our proprietary in silico platform BEYOND to generate novel therapeutics to hit previously undruggable targets. We're pioneering an engineered approach to drug discovery by scaling quantum simulations and fusing them with generative chemistry to tackle previously undruggable, high-impact targets.

Our team of pioneering scientists, engineers, drug hunters and quantum chemists values passion, teamwork, out of the box thinking and determination to solve even what seems impossible. We embrace diversity and are committed towards inclusion.

Position Overview

We are seeking an exceptional Senior Computational Data Engineer to join our team of pioneering scientists, engineers, drug hunters and quantum chemists to design, build, and scale the data infrastructure powering our proprietary BEYOND platform. This role is critical to transforming complex computational and experimental results into the organized, high-quality data foundation for our state‑of‑the‑art AI/ML and generative molecular design capabilities.

The ideal candidate blends strong engineering expertise with foundational knowledge in chemistry and computational drug discovery.

• Design, implement, and deploy software for the computational data generation and management of our proprietary computational and experimental data
• Systematize and scale our ongoing efforts to generate large datasets of computational predictions that form the basis of BEYOND’s state‑of‑the‑art force field and AI/ML models
• Incrementally automate all steps related to data generation, collection, transformation, storage, and final incorporation into BEYOND’s AI/ML models
• Develop web APIs and related tools to make these datasets accessible programmatically
• Carry out software engineering best practices, including code review, testing, and writing documentation
• Facilitate cross‑functional collaboration through clear, effective communication of technical requirements and solutions

• 5+ years of professional data engineering, data science, or software development experience
• Proven track record of delivering software projects on time and that meet the requirements

• An excellent grasp of, and complete comfort using, Linux operating systems
• Expertise in shell, Python 3, and SQL programming languages and related technologies
• Experience with Python web and database libraries (FastAPI, psycopg, etc.) and related protocols (HTTP, relational databases)
• Experience with software development best practices (version control/Git, code reviews, static analysis tools)

• Undergraduate-level knowledge of chemistry, statistics, and math
• Familiarity with the process of developing AI and ML models, especially data generation, management, curation, and storage
• Experience with cheminformatics and molecular property prediction

• Excellent communication skills with the ability to effectively collaborate across functional boundaries, serving as a technical bridge between scientists, engineers, and drug designers
• Passion for solving complex, seemingly impossible problems and the ability to work effectively at the intersection of science, AI/ML, and engineering, coupled with a strong interest in continuous learning and pushing technical boundaries

• First hand experience developing and deploying AI/ML models
• Familiarity with reinforcement learning, LLMs, and other AI/ML concepts
• Experience using cloud computing platforms such as AWS
• Experience with shared HPC computing environments, such as SLURM
• A familiarity with some of the major challenges and approaches in computational drug design
• Familiarity with Quantum Mechanics, molecular force fields, molecular dynamics, and the common file formats used in structure‑based drug design
• Additional programming skills, such as facility with other programming languages or popular Python programming tools, for example numpy, scikit, rdkit, and PyTorch or libraries…