Sam Deluca
Principal Software Engineer at Iambic Therapeutics
Washington DC-Baltimore Area United States
Summary
👤
Senior🎓
Top SchoolSam Deluca is a Principal Software Engineer with 15 years of experience building high-throughput, production-grade systems that span molecular modeling, cloud deployments, and security stream processing. He blends deep computational structural biology (PhD from Vanderbilt) with hands-on engineering—having developed RosettaHTS for virtual high-throughput screening and led engineering teams at Cyrus Biotechnology and CloudLock. Currently focused on bringing state-of-the-art molecular modeling into the cloud at Iambic Therapeutics, he pairs expertise in C++, Python, MPI and ML techniques with practical MLOps experience (notably improving OpenFold deployment and multi-model execution). As a former CEO and long-time contributor to bioinformatics tooling, he’s comfortable shipping both research-grade algorithms and robust, scalable infrastructure. Colleagues rely on him to translate complex numerical methods (Monte Carlo, gradient minimization, neural classifiers) into reliable, deployable systems that run on large clusters.
15 years of coding experience
12 years of employment as a software developer
BS, Bioinformatics/Molecular Biology, BS, Bioinformatics/Molecular Biology at Rensselaer Polytechnic InstituteDoctor of Philosophy (PhD), Computational Structural Biology, Doctor of Philosophy (PhD), Computational Structural Biology at Vanderbilt University
Github Skills (6)
continuous-deployment10
docker10
python10
dockers10
ml-deployment10
pytorch9
Programming languages (8)
Github contributions (5)
aqlaboratory/openfold
Feb 2022 - Dec 2022
Trainable, memory-efficient, and GPU-friendly PyTorch reproduction of AlphaFold 2
Role in this project:
MLOps Engineer
MLOps EngineerContributions:3 reviews, 21 commits, 6 PRs in 10 months
Contributions summary:Sam primarily focused on improving the deployment and usability of the openfold project, specifically with the addition of a Dockerfile build, bug fixes in run scripts and model execution. The user also refactored the `run_pretrained_openfold.py` script to allow for the execution of multiple models and fixed several bugs to ensure it worked correctly. These changes demonstrate a focus on streamlining the model's execution and deployment within the OpenFold project.
pytorchmemorygpualphafoldreproduction
decarboxy/py_protein_utils
Jan 2011 - Sep 2011
Contributions:120 commits in 8 months
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.