Professional Overview
AI engineer who ships production agentic systems end to end. I architected and run the platform behind a legal-AI product serving ~3,500 users across South Africa and Namibia: LangGraph StateGraph workflows, DSPy MIPROv2 pipelines with promotion gates, multi-tenant Weaviate retrieval, and 30+ Airflow DAGs in production.
Experience
AI Expertise
Skills
Employment Type
Description of Responsibilities
- Direct AI strategy across Murphy's Law, DISH, and RMB Bank production stacks
- Lead R&D: A2A multi-agent prototypes, Cognee plus Neo4j graphs, multi-LLM
- Own architecture, production code, and client conversations end to end
Key Achievements / KPIs
- Scaled Murphy's Law legal-AI to ~3,500 users across South Africa and Namibia
- 30+ Airflow DAGs across 4 production systems; authored 2 Helm charts
AI Expertise
Skills
Employment Type
Description of Responsibilities
- Built Murphy's Law core: 5 LangGraph StateGraph workflows + 16 Airflow DAGs
- Shipped DSPy production pipelines with MIPROv2 prompt-optimization gates
- Multi-tenant Weaviate hybrid retrieval; query rewriter lifted accuracy 40%
Key Achievements / KPIs
- Cut CI/CD release cycles ~95% preprod, ~75% production on Azure DevOps
- Shipped kvell-extraction PyPI tool: 12+ formats, 85% faster than OCR
AI Expertise
Skills
Employment Type
Description of Responsibilities
- Architected Murphy's Law: Azure AKS, 105k-LOC FastAPI backend, Next.js front
- Authored production Helm charts for Rand Merchant Bank AKS infrastructure
- Deployed LiveKit WebRTC voice agent with swappable multi-LLM backends
Key Achievements / KPIs
- Stood up RMB Bank AI platform: 7 Azure DevOps pipelines, 9 AKS namespaces
- Built voice subsystem on xAI Grok Realtime with Postgres advisory locks
Education
Field of Study: Artificial Intelligence
Field of Study: Statistics and Data Science
Field of Study: Computer Science and Engineering
Areas of Expertise
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.
MLOps & AI Infrastructure
Architect scalable ML infrastructure — CI/CD for ML, model versioning, experiment tracking, monitoring, and cloud deployment on AWS, GCP, or Azure.
Automation & AI Workflows
Build intelligent automation pipelines, integrate AI APIs into existing tools, and replace manual workflows with agentic AI systems.
AI Product & Strategy
Translate AI capabilities into product roadmaps, define success metrics, and drive adoption across engineering and business teams.
