Curriculum vitae

Backend Software Engineer Intern

• Fixed a production video moderation agent that often flagged entire videos instead of the violating segment, raising precise timestamp output from 72% to 91% by enforcing structured JSON output and fixing a validation bug.
• Built a 3,900-case benchmark to test whether retrieving past moderation decisions (RAG) improves an LLM moderation agent, and prototyped an autoresearch agent that lets ops teams run their own experiments.
• Added token, latency, and cache metrics and a Grafana dashboard to a Go captioning service to track LLM cost.

Co-founder

• Built a voice-agent evaluation framework to compare agent quality across simulated conversations using automated scoring and Langfuse trace analysis.
• Developed form analytics, document-to-form generation, and real-time voice-agent pipelines with TypeScript, FastAPI, and Pipecat.

Software Developer, National Service

• Built an LLM-powered exam-marking platform with custom RAG over exam materials that reduced instructor grading time by over 50% in an air-gapped environment.
• Improved grader accuracy and robustness by benchmarking prompts and automating prompt optimization with DSPy and open-source data.
• Integrated Langfuse telemetry to monitor traces, latency, and scoring quality, reducing time spent debugging the pipeline.

Co-founder

• Built a neural search API for unstructured enterprise documents with Elasticsearch, ONNX Runtime, Jina, FastAPI, and MongoDB, supporting public-sector and enterprise pilots.
• Improved document-layout detection throughput by 400% by distilling and quantizing an RTMDet model for production inference.
• Deployed pilot systems on GCP and refactored services for self-hosted environments to enable on-premise adoption with SkillsFuture SG, NSCC, and Coherent, Inc.

Software Engineer Intern

• Built an internal MLOps model hub with Vue.js, FastAPI, and MongoDB that let teams deploy ML models as Kubernetes services.
• Automated deployment to air-gapped Kubernetes environments with Skaffold, Helm, and service-scaling APIs for 2 departments.
• Established a GitHub Actions CI pipeline for unit testing and linting to improve code quality and release confidence.

B.Comp. Computer Science

NUS Global Merit Scholarship. GPA 4.79/5.0.

Diploma in Applied AI and Analytics

GPA 4.0/4.0; Singapore Computer Society Silver Medal.

President

• Leading the entrepreneurship interest group of Residential College 4, NUS.

Coreteam

• Ran workshops for the student hacker community, including an introduction to Vim and a two-part series on end-to-end deployment.

Co-founder & Operations Head

• Co-founded an AI Singapore student chapter and organised a Machine Learning Bootcamp and a Deep Learning workshop; SPAI won an SP Excellence Award in its first year.