AI/ML Engineer | Applied AI Researcher | Advanced RITTech MBCS | Full-Stack AI Systems | Generative AI, RAG & Agentic AI | Human-in-the-Loop AI | MLOps | AWS & Azure
Advanced RITTech registered professional and Professional Member of BCS, The Chartered Institute for IT (MBCS), and Professional Member of IEEE and the IEEE Computer Society.
I design and build end-to-end, production-oriented AI systems across Machine Learning, Generative AI, Retrieval-Augmented Generation (RAG), Agentic AI, Human-in-the-Loop AI, multimodal AI, LLM fine-tuning, MLOps, cloud engineering, and trustworthy AI.
My current work includes enterprise knowledge automation, decision intelligence, governed AI workflows, MCP integrations, multimodal recommendation systems, fraud detection, and applied AI research.
- AI/ML Engineering: Machine Learning, Deep Learning, model evaluation, feature engineering, recommendation systems
- Generative AI & RAG: LLM applications, embeddings, vector retrieval, pgvector, grounded generation, citation validation
- Agentic AI & HITL: LangChain, LangGraph, stateful workflows, tool calling, approval workflows, Human-in-the-Loop AI
- MCP & Governed Automation: governed tool integration, controlled execution, safety gates, auditability
- Backend & Full-Stack AI: Python, FastAPI, PostgreSQL, React, TypeScript, Next.js
- MLOps & Cloud: Docker, Kubernetes, Terraform, GitHub Actions, CI/CD, monitoring, AWS, Azure
- Trustworthy AI & Governance: evidence sufficiency, abstention, deterministic controls, AI governance, auditability
- Data & Workflow Engineering: SQL, pandas, Kafka, Airflow, data validation, ETL, observability
- BCS Advanced RITTech — Professional Registration
- BCS, The Chartered Institute for IT — Professional Member (MBCS)
- IEEE & IEEE Computer Society — Professional Member
Trustworthy Human-in-the-Loop multi-agent systems, reliable RAG, AI governance, evidence sufficiency and abstention, safe execution, LLM adaptation, and auditable enterprise AI.