Experience
Technical ownership, production delivery, research, and teaching
ML Engineer
Tensor Auto · San Jose, CA
Role scope. Sole technical owner of three company-level ML/CV systems spanning multimodal calibration and in-cabin perception. I take each system from initial requirements and data contracts through independent design and implementation, partnering with infrastructure and testing teams at system boundaries; two have reached onboard production deployment, while the third remains in active validation and integration.
Product Definition & System Design
Partnered with my manager to translate high-level product direction into concrete system requirements, evaluation criteria, integration contracts, and delivery milestones.
End-to-End Technical Ownership
After aligning on high-level product direction, independently translated it into concrete requirements and implemented the core data, geometry, model, training, evaluation, and runtime components for all three systems.
Data Infrastructure Collaboration
Partnered with the data infrastructure team to define sensor-data formats and interfaces, validate upstream data quality, and co-develop automated data-collection tooling for scalable training and evaluation.
Production Deployment
Owned model export, TensorRT optimization, onboard C++ integration, release validation, deployment support, and production monitoring across the complete inference path.
Validation & Integration Debugging
Worked directly with the testing team to design integration tests, reproduce system failures, debug data/model/runtime issues, and verify fixes in the integrated environment.
Production Robustness
Hardened model outputs with validation logic, consistency checks, deterministic interfaces, and failure diagnostics to improve reliability beyond offline model accuracy.
Technical details and results are documented in the corresponding case studies.
Research Assistant
University of Rochester · Jan 2023 — May 2024 · Advisor: Professor Tong Geng
- Developed PyTorch-based graph learning and nature-inspired computing methods, combining algorithm design, mathematical analysis, and controlled experimentation across multiple application domains.
- Designed reproducible research workflows for model comparison, performance analysis, and collaborative experimentation in shared Linux computing environments.
- Led a five-member research infrastructure effort covering Linux server administration, automation, Docker/Kubernetes environments, and reliable access to shared compute resources.
Teaching Assistant
University of Rochester · 2022 — 2024
Delivered lectures, discussion sessions, office hours, and laboratory support across multiprocessor systems, memory architecture, computer organization, and electronic circuits. Guided students through technical work in C, MIPS assembly, Verilog, SPICE/LTspice, and hardware debugging.