Hello, I'm Pengcheng Wang
Ph.D. Candidate · Elmore Family School of ECE · Purdue University
My research focuses on optimizing Machine Learning Systems (MLSys) for performance and energy efficiency on embedded GPUs, server GPUs, and AI accelerators. I work on Vision-Language Models (VLMs), Large Language Models (LLMs), and Computer Vision.
Optimizing latency, accuracy, and energy efficiency for real-world ML deployment.
🎯 Actively seeking 2026 Summer or Fall full-time opportunities as a Machine Learning Engineer or Research Scientist, focused on ML systems optimization and efficient inference for vision & language models.
⚡ Research Interests
- Resilient and Adaptive Vision-Language Model (VLM)
- Resource-Efficient VLM/LLM Inference
- Machine Learning Systems (MLSys)
🎓 Education
- Ph.D. Candidate, Purdue University
West Lafayette | 2019 ~ Now - M.S., Tongji University
Shanghai | 2014 ~ 2017 (Excellent Graduate) - B.E., Tongji University
Shanghai | 2010 ~ 2014 (Excellent Graduate)
🏢 Work Experience
- Machine Learning Engineer Intern at EmbodyX Fall 2025
- Built foundation models for robotic systems
- Optimized VLM inference using token compression
- Applied model compression for efficient deployment at scale
- Software Engineer Intern - AI ToolChain at Sunlune Spring & Summer 2025
- Developed and validated kernel, runtime, and driver software frameworks for AI accelerators
- Integrated kernels and optimized runtime workflows to enable efficient inference of Llama-family LLMs
- Performed feature testing, performance tuning, and cross-platform debugging
- Generative AI Model Intern at Sunlune Summer & Fall 2024
- Developed AI-enabled design flow for high-performance digital circuit design
- Designed Reinforcement learning (RL) models for circuit generation
- Collaborated with IC design engineers to capture design experience with AI models
- Teaching Assistant at Purdue University Spring 2024, 2025
- ABE591: From Chips to Cloud: Machine Learning in IoT and Computer Systems
💻 Services
- Program Committee, KDD 2026 AI4Sciences Track
- Reviewer, Journal of Systems Architecture
- Shadow Program Committee of SIGMETRICS 2026
- Artifact Evaluation Committee, EuroSys 2026
- Artifact Evaluation Committee of MobiSys 2025
- Shadow Program Committee of EuroSys 2024
- Artifact Evaluation Committee of SenSys 2024
- Artifact Evaluation Committee of USENIX OSDI 2022 and ATC 2022
📫 Contact
