Luc Beck

Student at the University of PennsylvaniaHOME // 00

Luc Beck

Studying Computer Science with a concentration in Artificial Intelligence at Penn. Working on the intersection of Physics and AI.

EngineerResearcherBuilder

Dual pick-and-place robotic arms, reconstructing the Penn coat of arms.

01

About

Premise

Take a system apart and put it back together until you understand exactly how it works. Then build the version that should exist.

My interests sit where hard physics meets computational theory. In my scientific research, that means biophysics: I built mathematical models of how DNA-based polymers can be used to perform experiments (aka 'lab on a molecule'), which fed into a drug-discovery platform now developing therapeutics. Outside scientific research, I build systems that move and learn, like a robotic arm I built and taught to manipulate objects via imitation learning.

I'm also interested in societal problem solving through serial entrepreneurship.

The future of manufacturing: Systems that move, learn, and build.
02

Education

Institution
University of PennsylvaniaSchool of Engineering and Applied Science
Degree
B.S.E., Computer ScienceConcentration in Artificial Intelligence
GPA
3.95 / 4.00
Class of
2029
Coursework
Computer ScienceComputer Systems, Data Structures and Algorithms, Object-Oriented Programming
MathematicsProbability and Statistics, Linear Algebra, Discrete Mathematics, Multivariable Calculus
PhysicsMechanics, Electromagnetism
EconomicsMicroeconomics, Macroeconomics
Honors
U.S. Presidential ScholarOne of up to 161 students named nationally each year
Programs
Y Combinator AI Startup School, D. E. Shaw Connect
Tower of Hanoi, 4 disks, recursive solution.
03

Engineering

PROJ-01

Computer Vision-Based Learning for Autonomous Robotics

Used human demonstrations and an open-source computer vision model to generate rewards for autonomous pick-and-place robot policies. I built an evaluation pipeline combining CoTracker3 point tracking with centroid-distance reward functions, which separated successful from failed rollouts at 99.7% average precision across 100 labeled trials. Using the learned rewards to rank and filter robot-generated training data improved held-out task success by 71%.

Period
Summer 2026
PROJ-02

Bolo: Language Learning App

A cross-platform iOS and Android app for learning Odia, built with React Native and Expo on a Supabase backend. Interactive language-learning workflows, with learner progress that persists across mobile sessions.

Period
Sep 2026 to present
Stack
React Native / Expo, Supabase
PROJ-03

Robotic Arm + ACT Policy

Building a robotic arm and training an action-chunking-with-transformers (ACT) policy on it using Hugging Face / LeRobot. Still a work in progress.

Demo
x.com/lucjbeck
PROJ-04

Next: Robotic Hand

Building a dexterous robotic hand paired with an instrumented glove. The glove captures human hand motion so the robot can be trained directly on teleoperated demonstrations, giving it a path to develop the fine-grained manipulation that standard robot arms lack.

Teleoperation training loop: human glove drives the demo hand; the policy hand learns to match. Motor positions stream to the graph below.
04

Research

SPEC-01

DNA Nanoswitches for Drug Discovery

Wong Lab, Wyss Institute / Boston Children's Hospital / Harvard2023 to 2025

Three summers building a DNA-nanoswitch platform for therapeutic discovery. I derived polymer-physics and enzyme-kinetic models predicting nanoswitch conformational states, reaction rates, and binding equilibria, and used AlphaFold and Python to model nanobody-target interactions across autoimmune and viral pathways, quantifying mutation-driven changes in predicted binding affinity. I ran native PAGE gel-shift assays measuring binding enhancement of nanoswitch-discovered nanobodies on the PD-1/PD-L1 complex implicated in autoimmune disease. The platform has since spun into a company developing therapeutics, with candidates advancing toward clinical trials.

Publication

First authorJournal of Emerging Investigators

Accepted — Awaiting Publication

Tethered Molecular Interactions in DNA Nanoswitches: Modeling and Controlling Local Concentration. With Wesley Wong (Harvard Medical School) and postdoctoral researcher Andy Ward.

This paper investigates how spatial constraints influence molecular binding by using DNA nanoswitches, programmable DNA scaffolds that position binding partners at defined distances. By integrating gel-based experiments with a polymer physics model, we quantify how binding-site arrangement affects the probability of loop formation through changes in effective local concentration. The results provide a generalizable approach for predicting and controlling tethered biomolecular interactions in synthetic and biological systems.
DNA nanoswitch, simulated as a flexible polymer. A streptavidin analyte binds a biotin, the strand loops to bridge the second, then releases.
05

Experience

Summer 2026

Washington, DC

Construct Capital

Software Engineer & Investment Analyst

I architected and shipped the firm's internal investment automation platform, built on a centralized context layer that combines structured CRM data, company records, documents, and communications so AI agents can retrieve persistent firm context across automated diligence workflows. On top of it I built an agentic sourcing and triage pipeline that identifies stealth founders, enriches company profiles, and surfaces prospective investments, plus a self-diagnosing workflow that launches Claude Code sessions with application context and user-reported errors to investigate and repair bugs. Deployed on Railway, the platform cut manual work by an estimated 6+ hours per investor per week.

Sep 2025 to present

Philadelphia, PA

Locust Bioventures

Consultant, Wharton Undergraduate Entrepreneurship Club

Consulting on the spin-out of a Penn-licensed AI/ML computational biology platform.

Summers 2024 and 2025

Cambridge, MA

Northpond Ventures

Venture Capital Intern

I evaluated spinning DNA-nanoswitch drug-discovery technology out into a new company, Merge Bio, assessing platform scalability, IP positioning, and commercialization strategy. I built the financial model end to end, a risk-adjusted revenue build, DCF, and sensitivity analyses spanning market sizing, pricing benchmarks, and probability-of-success adjustments across clinical phases. I also authored the scientific positioning on nanoswitch-based therapies for Type 1 Diabetes, covering PD-1/PD-L1 agonist mechanisms and the competitive landscape. The work fed into a $15M seed round.