January 2026 - Present

• Built an email automation agent in LangGraph that classifies incoming sales emails and extracts structured records from PDFs, images, and spreadsheets in a single Gemini 2.5 Pro call, with the output schema enforced by Pydantic.
• Wired up the observability stack around it: MLflow 3.x for per-email traces and token cost, Prometheus + Grafana for queue depth, p95 latency, and monthly billing. Runs on FastAPI and async PostgreSQL inside Docker Compose.
• Deployed and configured Odoo 19 Community as the internal management and CRM system across two legal entities on self-hosted Docker infrastructure via Dokploy.
• Led an AI agent-assisted migration of 14 years of historical business data from Salesforce into Odoo, completed in 4 weeks.
• Building a separate POC for voice agents handling inbound and outbound calls; currently in review.

July 2025 - December 2025

• Took an internal customer-matching system from 37% to about 88% accuracy by reworking the matching logic and cleaning the underlying data.
• Cleaned and structured contact data for medical organisations before loading into Postgres for downstream queries.

December 2024 - June 2025

• Co-authored a peer-reviewed paper on phishing website detection (ICERIE-25). Random Forest with TF-IDF and Count Vectorizer features performed best on the imbalanced dataset.
• Drafted deep-learning architectures (RNN/LSTM) for real-time detection as a follow-up direction.