Professional Overview
I'm Head of Development at PeakAgent. As the first engineer, I took our multi-tenant AI agent platform from zero to production (about 50 isolated AI assistant deployments that business owners use over SMS, WhatsApp, email and phone) and built the engineering team. I design agentic systems end to end: planner/worker/verifier orchestration with tool calling, long-term memory with per-customer isolation, LLM routing across five providers, and real-time speech-to-speech voice with sub-second first audio and barge-in recovery. I'm currently building a document-automation agent that reads Gmail or Outlook (scans, photos, any attachment), files into Google Drive or OneDrive and asks only when unsure, on top of a vision-based document reader benchmarked at ~97% field accuracy. Every release is gated by evaluation suites and safety tests, designed for cost, latency and tenant security. Before PeakAgent I spent nearly four years shipping NLP, computer vision and LLM automation for US clients with Python, PyTorch, TensorFlow, FastAPI, Docker and MLflow. Open to full-time and contract roles in AI architecture and agentic engineering.
Areas of Expertise
AI Product & Strategy
Translate AI capabilities into product roadmaps, define success metrics, and drive adoption across engineering and business teams.
AI & Machine Learning Engineers
Design, train, and ship production ML models — from data pipelines to model inference at scale. Covers supervised learning, neural networks, LLM integration, and model optimisation.
Automation & AI Workflows
Build intelligent automation pipelines, integrate AI APIs into existing tools, and replace manual workflows with agentic AI systems.
