PhD Researcher · Melbourne, Australia
I build multi-agent reinforcement learning systems that coordinate under pressure — and that can explain themselves to the people depending on them.
My PhD builds hierarchical MARL for human–AI teaming in emergency response, at Deakin and Coventry. Before it, four years shipping production LLM pipelines and agent frameworks in industry — the research and the engineering keep each other honest.
Autonomous teams are becoming capable enough to act on our behalf in high-stakes settings. My work is about the part capability alone doesn't solve: coordinating a team of agents under pressure while keeping the human supervising them informed, in control, and not overloaded.
Doctoral research
Adaptive Human–AI Collaboration for Emergency Response
Coordination and task allocation when objectives shift mid-mission and communication is unreliable.
Autonomy that adapts to the person supervising it, rather than a level fixed at design time.
Reading workload, trust and intent from behavioural signals as a mission unfolds.
Keeping agent reasoning inspectable, and an agent's intent legible to the person beside it.
I write about the parts I can share on the blog. Ongoing thesis work is mostly under review — happy to talk about it directly.
Decentralised training keeps replicas in step by periodically averaging a random subset of their weights. Existing guarantees assume a replica both contributes to the average and receives the result — separate communication events that fail independently in practice. Separating them reveals an asymmetry: receive failures weaken agreement linearly, while send failures instead displace the value replicas agree on, a second channel doubly stochastic mixing cannot represent. The admissible step size is therefore smaller than previously stated.
A knowledge-graph-driven agentic framework that combines cultural emotion knowledge, valence–arousal–dominance annotations and reinforcement learning to produce emotionally sensitive, culturally adaptive responses — cutting cultural representation bias by 61% and improving sentiment alignment over baseline models.
Presented at the 6th International Conference on Advancements in Computing. A framework for strengthening the structured reasoning of large language models through agentic workflows, reaching state-of-the-art results on reasoning tasks.
Further work from the PhD is in preparation. The current list is on Google Scholar.
Long-form notes on things I've built and what broke along the way — including the failures, which are usually the useful part.
Tertiary Student Projects: Solutions · Bandar Seri Begawan, Brunei Darussalam
Regional recognition across the Asia Pacific for FootEdge Pro, an AI-powered soccer performance analysis tool automating event detection, player tracking and advanced match analytics.
Tertiary Category · Sri Lanka
National recognition for innovation and technical development in sports analytics, and the qualifying route to APICTA.
6th International Conference on Advancements in Computing
For CARA, on the contribution of swarm agentic workflows and knowledge graphs to large language model reasoning.
Faculty of Engineering, University of Sri Jayewardenepura
Recognising employability, leadership and technical ability across the graduating engineering cohort.
Earlier: finalist at TadHack Sri Lanka 2022 as team lead, top three at INTELLIHACK Master, Most Popular Idea at INTELLIHACK 2, and finalist at CS‑INSL 2022.
Department of Data Science & Artificial Intelligence · Research Assistant
Designing a causal trust model for multi-agent reinforcement learning environments, pairing a discriminative teacher–oracle trust signal with a learned concept bottleneck. Building a neuro-symbolic concept layer and a causal trust graph so estimates generalise past a single teacher's behaviour, plus a domain adapter that carries the model across environment layouts.
Python · PyTorch · Causal inference · Symbolic reasoning · Multi-agent RL
Machine Learning Engineer · Sri Lanka
Architected and deployed RAG pipelines on LangChain, LlamaIndex, Pinecone and AWS, powering knowledge-management and chatbot ecosystems with 40% faster response accuracy. Engineered agent frameworks in AutoGen, CrewAI and LangGraph that removed over 60% of manual intervention, and built Markaive — a multi-agent platform that accelerated market research and content generation threefold.
LangChain · LlamaIndex · AutoGen · CrewAI · LangGraph · FastAPI · AWS · PostgreSQL
AI Engineer · Sri Lanka
Built transcript-analysis and note-generation modules on transformer summarisation and topic modelling, and optimised Fact Factory — an event summarisation engine running over millions of customer interaction records — to sub-second latency. Integrated LLM pipelines across multi-tenant systems using asynchronous microservices.
PyTorch · BERT · LDA · FastAPI · AWS · MongoDB · Hugging Face
Machine Learning Engineer, contract · Sri Lanka
Automated marketing report generation with AI agents, lifting campaign efficiency and ROI, and deployed NLP models for data-driven marketing strategy on LLaMA 3 and Groq.
AutoGen · CrewAI · LangGraph · LLaMA 3 · Groq
Associate Machine Learning Engineer · Sri Lanka
Engineered InsurePULSE, an AI system for insurers spanning backend ETLs, report generation and cloud deployment. Built Docufy, a document query tool for HR firms on LangChain and Elasticsearch, a sensitive-data filtering layer for enterprise chat systems, and ML models across finance and medical domains.
FastAPI · Azure · PostgreSQL · Elasticsearch · Kafka · React
AI Engineering Intern · Sri Lanka
Built information extraction and verification models for national identity documents, contributed predictive models to AI‑CORE, and co-authored a research paper on AI-driven ID card verification.
PhD, cotutelle — Information Technology · Melbourne & Coventry
BSc Engineering, Honours · Colombo
Multi-Agent Reinforcement Learning · Hierarchical RL · Human–AI Teaming · Theory of Mind Modelling · Multimodal Learning · Large Language Models · Knowledge Graphs · Explainable & Trust-Aware AI
Unreal Engine 5 · StarCraft Multi-Agent Challenge · Google Research Football · Overcooked-AI · PettingZoo · Gymnasium · RLlib · Ray
Python · PyTorch · TensorFlow · FastAPI · LangChain · LlamaIndex · AutoGen · CrewAI · LangGraph · Hugging Face · vLLM · DeepSpeed · LoRA / PEFT · Weights & Biases · MLflow · Pinecone · Qdrant · FAISS · AWS · Docker · Kubernetes · PostgreSQL · MongoDB · Redis
I speak often about agentic systems, reasoning, and what actually survives contact with production.
CENSOC — University of Sri Jayewardenepura
University to Industry Orientation — Faculty of Engineering, USJ
Build with AI — GDG Sri Lanka
Global AI Bootcamp — Colombo
MLOps Community — Sri Lanka
Google I/O Extended — GDG Sri Lanka
Global AI Bootcamp — Colombo
Omdena Sri Lanka Chapter — led AI-driven community projects
SEDS Sri Lanka — Aeronautical Division
I’m always glad to hear from people working on multi-agent RL, human–AI teaming, or anything nearby — collaborations, reading groups, benchmark comparisons, or a good argument.
