Learning-Based Locomotion Control
Developing reinforcement-learning and policy-optimisation controllers for quadruped and humanoid locomotion in Isaac Lab and MuJoCo.
- Reinforcement Learning
- Isaac Lab
- MuJoCo
- Robotics
AI/ML and software engineer in Singapore

Computer engineering graduate student working across machine learning, data systems, robotics simulation, and full-stack development.
Selected work
Developing reinforcement-learning and policy-optimisation controllers for quadruped and humanoid locomotion in Isaac Lab and MuJoCo.
Four machine-learning analytics modules and a conversational interface built on procurement data spanning eight source tables.
An ESP32 and MicroPython monitoring pipeline using MQTT, ThingSpeak, and MATLAB to classify normal and failure states.
NSGA-II across four benchmark and engineering problems, including a three-objective crashworthiness model with five design variables.
A Yelp-style discovery platform combining dining, events, weather, cost, and crowd signals through real-time services and Elasticsearch.
Experience
Jun 2025 — Aug 2025
Built an ML-powered procurement intelligence workflow on SAP purchase-to-pay data.
May 2024 — May 2025
Applied NLP and unsupervised learning to large-scale legal and political-science datasets.
Aug 2024 — Nov 2024
Created a Python order-tracking application used across two first-year engineering courses.
Sep 2023 — Jan 2024
Guided 50+ students through data structures, graphs, recursion, asymptotic analysis, and abstract data types.
Sep 2023 — Nov 2023
Mapped 15+ customer needs across three innovation sprints and supported AI-enabled improvement proposals.
About
I work across machine learning, simulation, connected hardware, and full-stack software. The common thread is straightforward: understand the problem deeply, then build the clearest useful solution.
Aug 2025 — Present
Jan 2022 — May 2025