Gihan Gamage
I build production LLM and agentic systems: document intelligence, retrieval and multi-agent automation for enterprises.
- Melbourne, Australia
- LLM & agentic systems
- PhD in AI
- 2.5+ years in industry
WorkCurrent
AI Automation Engineer
Work
Data & AI Specialist
Education
Ph.D. in Natural Language Processing and Data AI
La Trobe full-fee scholarship recipient. 19 publications, including 6 journal articles and 2 best-paper awards.
Education
B.Sc. (Hons) Computer Science and Engineering
First Class Honours, 4th highest GPA in the department, top 2.1% of a 914-student cohort, Dean's list every semester.
Selected work
All projects →
Agentic RFP & Vendor Evaluation
Replaced a ~3-month manual tender review with an agentic workflow; ~4 hours of reviewer time saved per vendor response
A three-stage agentic workflow for procurement: completeness checking, rubric-based scoring and side-by-side vendor comparison, with human approval gates at every decision point.
- Airia.ai
- LLM-as-a-judge
- Human-in-the-loop
- Guardrails
- Prompt engineering
- +1
Large-Scale Unstructured Notes Processing
1M+ free-text notes and 1B+ tokens turned into a structured data space during a platform migration
A cloud LLM pipeline that summarised and extracted implicit and explicit fields from over a million unstructured member-conversation notes, built to feed a structured data model during a company-wide platform transition.
- AWS Bedrock
- Step Functions
- Lambda
- S3
- Claude 3.5 Sonnet
- +2
Intelligent Legal Document Processing
AUD 220k saved against vendor quotes: 10,000+ contracts and 130k+ pages processed for about AUD 5k of infrastructure
An automated extraction pipeline pulling 20+ structured fields from more than 10,000 heterogeneous contract documents, built to support a legal team contract cleanup that had been quoted as an outsourced project.
- AWS (S3, Textract, Lambda, Step Functions)
- Azure OpenAI GPT-4o
- LLM-as-a-judge
- Fuzzy scoring
- Apttus & Salesforce REST APIs
- +1
Writing
All posts →
Decouple the data from the artefact
For branded, template-heavy outputs like decks and dashboards, keep the artefact out of the model entirely: strip its data to JSON, let the agent update only that, and plug it back into the untouched shell.
Every agent needs a human: the sponsor model in Azure AI Foundry
Agent identities in Azure AI Foundry are bound to a named human sponsor who owns their access, configuration and lifecycle, and Foundry suspends the agents when that person leaves.
AI webapps beat AI APIs, and the gap is the harness
Why the same model feels smarter in ChatGPT or Claude than through your API call, and the five pieces of engineering you have to rebuild yourself to close the gap.
Microsoft AI Foundry, in plain terms
A tour of AI Foundry's model catalog, agent service and resource hierarchy, and why it replaces jumping across separate Azure services.
What are AI agents, really?
Reasoning, tool use and memory are the three capabilities that separate an agent from a plain LLM call, RAG, or a fixed pipeline.
Infrastructure as Code is a good friend of AI engineers
A RAG chatbot touches a dozen services with configuration that matters. IaC is how you deliver the same setup to the next team without starting from scratch.
About
More →I'm an AI engineer in Melbourne. I build large language model and agentic systems that run in production: document intelligence pipelines over millions of records, retrieval and multi-agent workflows, and the evaluation and guardrails that make their output trustworthy enough to act on. My PhD is in artificial intelligence, where I worked on neuro-symbolic architectures for natural language comprehension, and I still teach postgraduate AI.
Contact
Open to AI and machine learning engineering roles, and happy to talk through any of the work here in more detail. Find me on LinkedIn, GitHub, or Scholar.