Building Intelligent AI Systems.Engineering Data-Driven Products.Delivering Real-World Impact.
I am a Senior AI & Data Engineer specializing in Python, Generative AI, Agentic Systems, RAG architectures, and scalable data platforms. I transform complex business problems into intelligent, reliable, production-ready solutions.
- 9+ yrs
- software & data engineering
- ~93%
- less time per policy extraction
- ~95%
- benefit classification accuracy
- 5,000+
- policies processed per month
Introduction
An engineer who ships the whole system, not just the model call.
I have spent 9+ years building software in Python — first data and backend systems, and for the last several years Generative AI applications in the insurance and benefits domain.
I don't just experiment with AI. I architect, engineer, integrate, deploy, and deliver production-ready AI and data solutions.
Most AI projects stall between a promising prototype and something a business can rely on. That gap is engineering: data pipelines, APIs, evaluation, deployment. It is the part I do.
More about my background- 01
Business problem
Clarify the outcome, the users and what 'good' looks like.
- 02
Architecture
Choose the simplest design that meets the requirement.
- 03
AI engineering
Prompts, retrieval, agents and evaluation built together.
- 04
Backend & APIs
Typed, tested Python services around the model.
- 05
Data pipelines
Reliable ingestion, transformation and quality gates.
- 06
Testing
Regression sets for both code and model behaviour.
- 07
Deployment
Containers, CI/CD, observability and cost tracking.
- 08
Delivery
Documentation, handover and a system your team can run.
Expertise
Where I am most useful
Six areas, all backed by delivered work. The technology list further down shows exactly how deep each tool goes.
Document intelligence
LLM pipelines that turn unstructured documents into validated, structured data.
RAG architectures
Retrieval, re-ranking and grounded generation, measured against real questions.
Agentic systems
Tool-calling agents and MCP integrations with clear permissions and approval steps.
Data platforms
PySpark, AWS Glue and Databricks pipelines with quality gates built in.
Python backends
FastAPI services, integrations and authentication around the AI layer.
Production delivery
Containers, CI/CD, evaluation and cost tracking — built to keep running.
Selected work
Projects and products
Case studies with the problem, the architecture and the result. Client names are withheld; figures are only shown where they were measured.
AI-Powered Insurance Policy Intelligence Platform
Reads insurance policy documents and returns structured, classified benefit data through an API.
- policies processed per month
- 5,000+
- policies processed per month
- extraction time per policy (about 93% less)
- 4 h → 15 min
- extraction time per policy (about 93% less)
- accuracy in benefit identification and classification
- ~95%
- accuracy in benefit identification and classification
- Python
- FastAPI
- Azure OpenAI
- LangChain
- Azure AI Search
RAG-Based Benefit Matching Engine
Aligns extracted benefits to a standard catalogue using semantic retrieval and fuzzy matching.
- of catalogue alignment automated
- ~85%
- of catalogue alignment automated
- Python
- LangChain
- ChromaDB
- Hugging Face embeddings
- Sentence Transformers
HBB File Transformation Engine
Turns raw, inconsistent benefit data files into industry-standard Excel output automatically.
- Python
- Pandas
- Regex
- OpenPyXL
- Excel automation
AI Code Auditor — Multi-Agent Engineering System
A multi-agent architecture for auditing a code repository: quality, security, architecture and reporting.
- Python
- LLM tool calling
- Agent orchestration
- AST / static analysis tools
- Git
Services
How I can help
Freelance and consulting engagements, from a focused architecture review to a complete build.
Generative AI Development
LLM applications that do a specific job well — grounded in your data and measured against real examples.
Agentic AI Engineering
Agents and tool-calling systems with clear boundaries, approval steps and full traceability.
Data Engineering
Pipelines that are correct first and fast second, with quality checks built in from the start.
Python Backend Development
Clean, typed FastAPI services and integrations — the layer that turns a model into a product.
AI Product Development
From an idea to a deployed MVP: architecture, backend, AI layer, a usable front end and cloud deployment.
AI & Data Engineering Consulting
An experienced second opinion before you commit budget — or when something is not working.
Experience
Recent roles
Nov 2023 — Present
Senior Software Engineer / Senior AI Engineer · Solugenix
GenAI and agentic AI delivery for regulated enterprise clients: a benefits document intelligence platform for a global consulting client and a finance platform for a payments and data client, alongside AWS data engineering on a banking data migration.
Apr 2023 — Aug 2023
Senior Software Developer · Pinnacle Data Reliability
Built an analytics and visualization platform ingesting real-time data from 10+ sources, used daily by around 200 people.
Dec 2020 — Apr 2023
Technical Consultant · Netscore Technologies
Data preparation and engineering for quantitative portfolio-management workloads.
Technology
Technology ecosystem
Grouped by real depth of use. Core means years of production work; Working means used on delivered projects; Exploring means lab and side work.
Generative & Agentic AI
Core
- RAG pipelines
- LLM-based extraction
- Azure OpenAI
- LangChain
- Azure AI Search
- Multi-query & hybrid retrieval
- Prompt engineering & versioning
- Document intelligence
Working
- MCP servers & clients
- AWS Bedrock AgentCore
- LangGraph
- Multi-agent orchestration
- Langfuse
- LLM-as-judge evaluation
- LLMOps & cost tracking
- Semantic caching
- Structured outputs
- ChromaDB
- Hugging Face embeddings
Exploring
- Anthropic Claude
- Google Vertex AI
- Ollama
- FAISS
- Meta LLaMA
- PyTorch / scikit-learn
Data Engineering
Core
- PySpark
- AWS Glue
- ETL / ELT design
- Data quality gates
- Schema standardization
- PostgreSQL
Working
- Databricks Lakehouse
- Apache Airflow (MWAA)
- Azure Data Factory
- Synapse Analytics
- SQL Server
- MongoDB
- Pandas
Exploring
- Medallion architecture patterns
- Unity Catalog
- Microsoft Fabric
- BigQuery
- AWS Step Functions
Python & Backend
Core
- Python
- FastAPI
- REST API design
- Async services
Working
- Flask
- Django
- SQLAlchemy
- RabbitMQ
- RBAC
- SAML SSO
- Streamlit
Cloud & Delivery
Core
- AWS
- Microsoft Azure
- Docker
- Git
Working
- Kubernetes
- Azure DevOps CI/CD
- API Gateway
- S3
- SonarQube
- Observability & cost tracking
Exploring
- Google Cloud Platform
Have an AI or Data Engineering challenge? Let's turn it into a working product.
Taking on a limited number of AI and data engineering projects. Typical reply within 2 business days.