WORK EXPERIENCE
WiseTech Global
Apr 2025 – Jun 2026
AI Engineer - AI/ML Group
- Built two agentic LLM systems for production customer support: CWBot, a support chatbot, and TriageAgent, an automated ticket-triage agent — combining LangGraph orchestration, FastAPI, Azure OpenAI, and durable PostgreSQL-backed state.
- Designed RAG workflows with dynamic question rewriting, custom retriever factories, and Azure AI Search integration over heterogeneous internal data sources to improve how users find and act on operational knowledge.
- Implemented guardrails for PII filtering and response steering, plus checkpointing and recovery patterns for reliable multi-turn product experiences.
- Maintained quality through systematic testing and evaluation: coverage across backend, frontend, and system test sets, with linting, type checks, and release-readiness quality gates.
SGLang Framework
Feb 2025 – Present
Open Source Contributor
- Contributing core optimizations to the SGLang LLM inference framework (LMSYS / UC Berkeley) for state-of-the-art models including DeepSeek R1, Llama 3, and Qwen.
- Leveraging AI coding agents (Claude Code) to navigate the large codebase, draft PRs, and review diffs in a human-in-the-loop open-source workflow.
ANZCC · AI Accounting Workshop
Jun 2026
Guest Speaker — AI for Accounting Professionals
- Designed and delivered a hands-on workshop introducing AI tools and agentic workflows to accounting professionals, adapting technical content for a non-technical business audience (published at /anzcc-workshop).
Australia IT Group · AI Engineer Bootcamp
Feb 2026 – May 2026
Guest Instructor & Curriculum Designer — RAG, Multi-Agent Systems, Fine-tuning
- Delivered 12+ sessions on production RAG, embeddings & vector search, RAGAS evaluation, multi-agent systems (LangGraph, AutoGen, CrewAI), QLoRA fine-tuning, and applied AI (UI, PDF parsing, Text-to-SQL); all notebooks and slides committed to the cohort repo.
- Designed Dispatch.AI, a 6-week hands-on course project, mentoring 13 students as they built a production AI booking assistant incrementally — Pydantic state + Redis persistence, LangGraph agents, MCP tool server, multi-agent routing, NeMo Guardrails, RAGAS evaluation, and Docker + Render capstone; delivered the reference implementation, scaffold, and CI/CD grading pipeline.
Redbubble
Mar 2023 – Jan 2025
Data Scientist - Search & Recommendation Team
- Designed and shipped search and recommendation experiments across a global e-commerce marketplace using Marqo vector search and GCP Vertex AI MLOps pipelines, lifting add-to-cart rate by 0.5% and CTR by 10%.
- Owned the full experiment lifecycle — analysis, offline evaluation, experiment design, deployment, post-launch metric review — collaborating with cross-functional product and engineering stakeholders and communicating results and model logic.
- Designed ML/data infrastructure processing 100M+ user events for feature engineering, search relevance analysis, and downstream serving workflows.
- Drove GA4 analytics migration on BigQuery to ensure data reliability across internal dashboard-driven A/B testing frameworks.
- Analyzed user behavior signals to optimize search relevance for long-tail queries, balancing retrieval quality against measurable business impact.
Redbubble
Jan 2021 – Mar 2023
Data Scientist - Content & Discovery
- Shipped production content-classification and moderation systems using language-image models, reducing intellectual-property moderation risk and improving operational throughput.
- Built duplicate-detection and data-quality/anomaly-detection pipelines (ML and statistical modeling), and mined engagement signals for taxonomy and SEO to improve product discovery.