Open to AI/ML & Applied AI roles · Manchester, UK

Building AI systems that retrieve, reason, and ship to production.

AI/ML Engineer with 10+ years in software engineering and 3+ years specialising in Generative AI, RAG, and Agentic systems for Financial Services and Automotive. MSc Artificial Intelligence, University of Aberdeen.

10+years in software engineering
3+years in generative AI & LLMs
76→94%model accuracy gains delivered

From problem formulation to production deployment.

I design, build, and ship end-to-end AI systems for enterprise use — not just notebooks. That means owning a problem from framing and model selection through evaluation, fine-tuning, and deployment into live products used by real teams.

Most of my recent work sits at the intersection of retrieval and reasoning: RAG pipelines, agentic multi-agent workflows built with LangGraph, and knowledge-graph-backed retrieval on Neo4j, layered on classic NLP and transformer fine-tuning when a smaller, cheaper model is the better answer.

  • Enterprise Generative AI applications
  • Retrieval-Augmented Generation (RAG) systems
  • Agentic AI & multi-agent workflows (LangGraph)
  • LLM fine-tuning — LoRA, QLoRA, PEFT
  • Semantic search & vector databases
  • Graph RAG & knowledge graph solutions
  • Intelligent document processing & enterprise chatbots

Systems shipped, not just prototyped.

Ten projects spanning generative AI, classification, agentic retrieval, and model optimisation.

GENERATIVE AI · AZURE OPENAI

Meeting intelligence platform

Built a summarisation tool on Azure OpenAI and LangChain that extracts key points directly from call transcripts, replacing manual note-taking for client-facing teams.

2enterprise clients secured
+25%revenue contribution
AGENTIC AI · GRAPH RAG

Multi-agent RAG & knowledge graph POCs

Designed LangGraph multi-agent workflows, Graph RAG on Neo4j, and multimodal PDF search with Qdrant/CLIP — proofs of concept that went on to shape the team's GenAI roadmap.

3POCs → roadmap
Multimodaltext + image retrieval
CLASSIFICATION · TRANSFORMERS

Text classification model optimisation

Evaluated and tuned ModernBERT, DeBERTa, and SetFit for production text classification, then re-architected the pipeline around OpenAI embeddings to cut training time without losing accuracy.

76→85%accuracy
4xfaster training (4.5h → <1h)
LLM ENGINEERING · PEFT / LoRA

LLM fine-tuning & sentiment classification

Optimised Flan-T5 and Mixtral with PEFT/LoRA for critical NLP tasks, and built a multi-class sentiment tool on GPT-3.5 Turbo using few-shot prompt engineering.

94%sentiment accuracy
-5%inference cost
RAG · AGENTIC AI

Enterprise-ready RAG system

Designed a production-grade Retrieval-Augmented Generation system with agentic orchestration on top, built for reliable, traceable answers over enterprise document sets.

RAGAgentic AIVector Search
MCP · TOOL USE

MCP-based agent integration

Built an AI project on the Model Context Protocol (MCP), connecting LLM agents to external tools and data sources through a standardised, interoperable interface.

MCPLLM ToolingAgents
AGENTIC AI · LANGGRAPH

Multi-agent system with LangChain & LangGraph

Orchestrated a set of specialised agents with LangChain and LangGraph to handle multi-step tasks that a single LLM call couldn't reliably complete end-to-end.

LangChainLangGraphMulti-Agent
FINE-TUNING · PEFT

LLM fine-tuning with LoRA, QLoRA & PEFT

Adapted open-weight LLMs to domain-specific tasks using parameter-efficient fine-tuning — LoRA, QLoRA, and PEFT — to cut compute cost versus full fine-tuning.

LoRAQLoRAPEFT
GENERATIVE AI · AWS

Generative AI series on AWS

Built and deployed generative AI applications on AWS, covering model hosting, orchestration, and integration into cloud-native services.

AWSGenerative AICloud Deployment
PROMPT ENGINEERING · AZURE OPENAI

Prompt engineering on Azure OpenAI

Designed and iterated prompting strategies on Azure OpenAI models to improve output reliability and task accuracy across a range of use cases.

Azure OpenAIPrompt Engineering

10+ years, four companies, one thread: shipping software that works.

AI/ML Engineer (NLP) — Recordsure JUN 2023 – PRESENT · LEEDS, UK
  • Built a meeting-summarisation tool on Azure OpenAI + LangChain, securing 2 clients and lifting revenue 25%.
  • Optimised Flan-T5 & Mixtral with PEFT/LoRA; improved BERT/SetFit classification accuracy from 76% to 85%.
  • Re-architected classification around OpenAI embeddings, cutting training time 4x.
  • Delivered a GPT-3.5 Turbo few-shot sentiment tool at 94% accuracy.
Senior Software Engineer — Finastra AUG 2016 – SEP 2021 · INDIA
  • Modernised legacy Loan Details & Check Hold applications, cutting runtime 30% and clearing 15 long-standing defects in one sprint.
  • Built a credit-card recommendation engine from purchase patterns, improving decision accuracy 30%.
  • Forecasted product success rates at 87% accuracy using customer sentiment & ML models.
Senior Engineer — Tata Elxsi APR 2015 – AUG 2016 · TRIVANDRUM
  • Built a user-action test framework and an internal tool auto-generating test case templates, cutting time 40%.
  • Promoted to Senior Engineer within 12 months.
Senior Software Developer — ThoughtLine Technologies MAR 2012 – MAR 2015 · INDIA
  • Designed and automated a client billing system in C# and SQL; optimised stored procedures for 2x faster retrieval.
  • Delivered billing automation for 3 new clients in a single month.

The stack, grouped by what it's for.

Generative AI

OpenAIAzure OpenAIGPT-4oPrompt Engineering

LLM Engineering

RAGAgentic AIGraph RAGLangChainLangGraphLlamaIndexMCPLoRA / QLoRA / PEFT

Machine Learning

NLPPyTorchTensorFlowScikit-learnTransformers

Vector & Graph DBs

FAISSChromaDBQdrantNeo4j

Cloud & MLOps

AzureAWSAzure MLMLflowDocker

Languages

PythonSQLC#

MSc Artificial Intelligence, Aberdeen.

2021 – 2022

MSc Artificial Intelligence

University of Aberdeen
2007 – 2011

BTech, Computer Science

University of Calicut
FinFame Award — zero-bug year-end delivery Finastra Global Hackathon — Runner-up Best Project Presentation Award Deep Learning with Keras & TensorFlow — Certified