Eeshwar Krishnan
Computer Science & Robotics Engineering
I am a Robotics Engineer
University of Michigan • Class of 2026
About
As a senior at the University of Michigan, I'm on a mission to revolutionize the intersection of AI and Robotics. My dual degree in Computer Science and Robotics Engineering fuels my passion for creating cutting-edge solutions to real-world challenges.
With a background in FIRST Robotics and a track record of innovation, I'm dedicated to pushing the boundaries of what's possible in technology.
Profile
Skills
Experience
Redux Robotics
Founder & CEO
Exton, PA
- • Pioneered development of next-gen robotics sensors with CAN network integration
- • Architected comprehensive firmware and API ecosystem for seamless user interaction
- • Innovated QC processes through automation, drastically improving product reliability
- • Optimized logistics pipeline, slashing average shipping time by 60%
KBR Consulting
AI Research Intern
Exton, PA
- • Developed a cutting-edge large language model powered solution for advanced records management
- • Engineered an AI-powered solution resulting in significant time savings across departments
- • Collaborated directly with department heads to optimize AI integration
ANSYS Government Initiatives
Software Engineering Innovator
Exton, PA
- • Engineered high-performance benchmarking infrastructure for mission-critical codebases
- • Created a system-invariant benchmarking framework for continuous performance testing on dev computers
UM::Autonomy
Lead Embedded Systems Architect
Ann Arbor, MI
- • Spearheaded development of robust electrical systems for autonomous boats
- • Conducted rigorous real-world testing, ensuring peak performance in extreme conditions
Research
A Novel Framework to Predict Protein Folding Using a Weighted Approach
This research introduces an innovative framework for predicting protein folding, combining various machine learning approaches through a principled weighted voting method. The study demonstrates a significant improvement in the accuracy of protein fold type predictions compared to individual methods.
Key Contributions:
- • Developed a weighted voting method to combine results from different machine learning approaches
- • Improved accuracy of protein fold measurements over individual methods
- • Contributed to the field of bioinformatics and structural biology
Education
University of Michigan
B.S. Computer Science
B.S. Robotics Engineering
Expected Graduation: May 2026 • Ann Arbor, MI