Expertise

AI & Agentic Systems

Designing AI systems that have to survive contact with real enterprise estates — real credentials, real APIs, real failure modes.

• LLM application and agent architecture
• Multi-agent orchestration and tool-calling gateways
• Retrieval-augmented generation and retrieval quality
• Embeddings, vector search and document ingestion pipelines
• Structured output and function calling
• MCP and A2A as enterprise integration surfaces
• Guardrails, evaluation and human-in-the-loop review
• Model routing and multi-model architectures

• Python
• Node.js
• AWS
• Azure
• PostgreSQL
• Redis

AI-Native Software Engineering

Changing how software gets built when agents are in the loop — without giving up the review discipline that makes it safe.

• Specification-driven development with AI agents
• AI-assisted architecture and documentation generation
• Legacy source and dependency analysis at scale
• Test generation with human validation gates
• AI-assisted code review and its limits
• Governance for AI-assisted delivery

• Claude Code
• MCP
• Git
• JavaScript
• Python

Cloud & Platform Engineering

The platforms underneath — designed for availability and cost, not for a diagram.

• AWS and Azure platform architecture
• Kubernetes and container orchestration
• Serverless and event-driven infrastructure
• High availability, networking and caching strategy
• CI/CD pipelines and deployment strategy
• Observability and operational readiness

• AWS
• Azure
• Oracle Cloud
• Kubernetes
• Docker
• Redis

Software Architecture

Enterprise systems that have to integrate with what already exists, and keep running while they change.

• Distributed and service architecture
• API and integration design
• Event-driven architecture
• Scalability and resilience patterns
• Legacy integration and incremental modernization
• Architecture review and technical decision records

• Node.js
• Java
• Python
• Go
• React
• PostgreSQL

Engineering Leadership

Leading the team that takes the engagements nobody else can unblock, and setting the standards the rest work to.

• Technical strategy and architecture governance
• Leading teams through complex, ambiguous delivery
• Mentoring engineers and architects
• Driving AI adoption without abandoning engineering discipline
• Technical decision-making and trade-off communication
• Engineering process transformation

Security

Security as an architectural constraint rather than a review gate at the end.

• Cloud and application security architecture
• Identity and access management
• Secure SDLC practice
• Credential isolation and secure tool execution for AI systems
• Network and perimeter architecture
• Security governance and review

• AWS
• Azure
• Check Point CloudGuard
• Kubernetes

Data

Data modelling and retrieval, including the pipelines that feed AI systems.

• Relational data modelling and query performance
• Document and key-value data design
• Vector search and embedding storage
• Document ingestion and RAG pipelines
• Caching strategy

• PostgreSQL
• Oracle
• SQL Server
• MongoDB
• Redis
• MySQL