Intern-AI​/ML in Antibody Developability Models

Job Function

Career Programs

Non-LDP Intern/Co-Op

Career Program

San Diego, California, United States of America

At Johnson & Johnson, we believe health is everything. Our strength in healthcare innovation empowers us to build a world where complex diseases are prevented, treated, and cured, where treatments are smarter and less invasive, and solutions are personal. Through our expertise in Innovative Medicine and Med Tech, we are uniquely positioned to innovate across the full spectrum of healthcare solutions today to deliver the breakthroughs of tomorrow.

About Innovative Medicine:
Our expertise in Innovative Medicine is informed and inspired by patients, whose insights fuel our science‑based advancements. Visionaries like you work on teams that save lives by developing the medicines of tomorrow. Join us in developing treatments, finding cures, and pioneering the path from lab to life while championing patients every step of the way.

About Med Tech:
Fueled by innovation at the intersection of biology and technology, we’re developing the next generation of smarter, less invasive, more personalized treatments. Your unique talents will help patients on their journey to wellness.

Johnson & Johnson Innovative Medicine is recruiting for a Summer Intern - AI/ML in Antibody Develop ability Models position in the Drug Discovery Data Science, In Silico Discovery (ISD) group in La Jolla, CA.

• The Intern term is from June to August, 2026.
• Full time requirement (40 hours per week).

The Drug Discovery Data Science group within the In Silico Discovery (ISD) organization in La Jolla, CA is seeking a current PhD student for a 10‑12 week Summer research internship. We are looking for a knowledgeable, self‑motivated, creative, and multi‑skilled graduate student with a strong interest in machine learning, data science, computational biology, and biotherapeutics discovery. In this role, the intern will design and implement machine learning frameworks that leverage public protein property datasets alongside internal experimental data to improve predictive models.

Thermostability and related properties will be key areas of focus.

• Collecting and curating large public datasets.
• Developing and engineering features by integrating sequence embeddings from state‑of‑the‑art protein language models and structure‑derived descriptors, as well as benchmarking alternative feature sets.
• Developing deep learning models to capture general physicochemical stability patterns.
• Applying transfer learning by fine‑tuning pretrained models on internal antibody thermostability datasets and rigorously evaluating predictive performance.
• Publication is encouraged.

• Completion of Undergraduate Freshman year at an accredited University is required.
• Have a cumulative GPA of 2.8 or higher, which is reflective of all college coursework.
• PhD student in computational biology, biophysics, machine learning, data science, or related field.
• Demonstrated experience in deep learning with proficiency in Python and PyTorch.
• Familiar with protein language models and key structural determinants of protein stability.
• Experience with transfer learning or working with pretrained deep learning models preferred.
• Familiarity with antibody structure and function is preferred.
• Strong communication, problem‑solving, and collaboration skills.
• Candidates must have authorization to work in the U.S.
• The individual should be able to work onsite at our La Jolla campus during the whole internship period.

Students currently on CPT, OPT, or STEM OPT usually require future sponsorship for long‑term employment and do not meet the requirements for this program unless eligible for an alternative long‑term status that does not require company sponsorship. Permanently authorized to work in the U.S., must not require sponsorship of an employment visa (e.g., H‑1B or green card) at the time of application or in the future.

The expected pay range for this position is between $26.50 per hour and $59.00 per hour but will be based on…