Senior Data and AI Engineer | Tech Lead | LLM Agent Systems | Kafka | Kubernetes | AWS

AI Engineering & LLM Agent Systems
Expertise in building and deploying LLM agent systems using LangGraph, LangChain, and Model Context Protocol (MCP). Development of multi-agent workflows, prompt engineering, agent evaluation, offline testing with pure-mock and record-and-replay modes, and GenAI delivery discipline for production-grade AI systems.

Streaming & Real-Time Data Platforms
Deep experience with Apache Kafka and AWS EventBridge for large-scale event streaming at automotive scale. Design and operation of real-time telemetry pipelines, push/pull data delivery architectures, Kafka backlog resolution, and migration from Azure Event Hubs to Kafka handling millions of events per day.

Cloud Infrastructure & Kubernetes
Extensive hands-on work with AWS, Azure, and Kubernetes for deploying and operating data and AI systems. Management of GitOps repositories using Helm, Flux, and Terraform across multiple Kubernetes estates, including formal operational handovers and CI/CD pipelines via GitLab.

Data Lake & Big Data Engineering
Design and implementation of distributed data lakes using AWS Delta Lake, Glue, EMR, Kinesis, Athena, and Apache Spark. Migration from legacy monoliths to data mesh architectures and management of large-scale Hadoop clusters.

MongoDB & Database Scaling
Leadership of MongoDB scaling programmes including reduction of billion-document collections, audit trail management, hot-collection sharding, and Atlas optimisation through per-index size analysis and container-backed write placement tests.

API Design & Security
Architecture and development of API suites with AsyncAPI/OpenAPI schema management, automated security test suites covering authentication, cross-organisation access control and injection, and behaviour-driven scenarios running in CI with published results dashboards.

Python & Backend Development
Proficiency in Python with FastAPI, Pydantic, and asyncio for building backend services and data pipelines. Additional experience with Java and Spring Boot for service development.

MLOps & Machine Learning in Production
Experience deploying and operating machine learning models in production since 2019, including ML model deployment on serverless AWS architectures, real-time Kafka pipelines feeding ML models, and fine-tuning with LoRA (in progress).

Observability & Performance Engineering
Evidence-first performance work using Datadog observability, measuring tens of millions of API requests per day, diagnosing memory leaks, and resolving production incidents through live capacity tuning and autoscaling configuration.

Architecture & Technical Leadership
Architecture design authority for platform products using C4 component diagrams, cross-team architecture decisions, threat assessments, penetration test scoping, and vulnerability remediation. Led multiple teams through formal operational handovers and product delivery.