I work at NatWest Groups
I’m currently working on
Production-grade Generative AI and MLOps systems for regulated financial environments.
• Building privacy-first RAG and LLM applications that run fully local (no data leakage)
• Designing multi-agent workflows using LangGraph for complex financial analysis
• Shipping reproducible ML pipelines with AWS SageMaker, CI/CD and automated retraining
• Hardening AI systems with security layers (PII redaction, audit logs, input validation, monitoring)
I’m looking to collaborate on
Enterprise AI problems where reliability, security and scale matter more than flashy demos.
• Production ML / MLOps architecture
• LLM systems (RAG, evaluation, inference optimization)
• FinTech, Risk, and Climate analytics
• Open-source tools for secure, compliant AI deployment
I’m currently learning
Advanced system design for large-scale AI.
• LLM evaluation frameworks (RAGAS, observability, guardrails)
• GraphRAG & knowledge graphs for structured reasoning
• Efficient inference & cost optimization
• Distributed pipelines and production monitoring
• Secure AI architectures for regulated industries
Fun Fact
I plan most of my system designs on a whiteboard before writing code, and I’m usually trekking in the mountains when I’m not debugging pipelines. Turns out both require endurance and patience.
