About Me

I'm an engineer and scientist who enjoys wrangling messy data, building ML systems, and pushing AI to be both smart and reliable.

I've deployed data backbones across organizations and spent years exploring models—from classical ML to LLMs and multimodal architectures. My current research centers on LLM verification: using knowledge-graph grounding and graph-based reasoning to turn opaque predictions into transparent reasoning chains that humans can trust.

I believe in AI that is intelligent but not confidently incorrect.

Experience

9+ Years

Data Engineering

Building scalable data infrastructure, ETL pipelines, and distributed systems across multiple organizations.

5+ Years

Machine Learning

From classical ML to deep learning, LLMs, and multimodal architectures. Research and production systems.

Expertise

AI/ML Research

  • Large Language Models (LLMs)
  • Retrieval Augmented Generation (RAG)
  • Explainable AI (XAI)
  • Case-Based Reasoning
  • Knowledge Graphs
  • Graph Neural Networks

Computer Vision

  • Vision Transformers
  • Synthetic Image Detection
  • Multimodal Learning
  • Image Classification

ML Engineering

  • PyTorch / TensorFlow
  • Hugging Face Transformers
  • MLOps & Experiment Tracking
  • Model Deployment
  • Distributed Training

Data Engineering

  • Apache Spark / Airflow
  • SQL / NoSQL Databases
  • AWS / GCP / Azure
  • Kafka / Streaming
  • ETL Pipeline Design

Current Focus

LLM Security & Trustability

Developing frameworks for automated penetration testing and secure deployment of generative AI systems in sensitive environments.

Knowledge-Grounded AI

Using knowledge graphs and structured reasoning to make LLM outputs verifiable and reduce hallucinations.

Financial ML (2026)

Preparing to work with financial trading datasets, exploring trustworthy AI for high-stakes decision making.