Available for new opportunities
Hargurjeet
Singh Ganger
Senior Data Scientist
Building production-grade LLM systems, RAG pipelines, and agentic workflows at British Telecom. 15+ years turning complex data into measurable business outcomes.
15+
Years Experience
TCS → Shell → BT
$10M+
Business Value Generated
Across AI & ML initiatives
100K+
Documents Processed
Multimodal, production scale
7+
AI Systems Shipped
In telecom, energy & IT
About Me
From IT Analyst to AI Systems Builder
At British Telecom I'm leading the Generative AI charge — deploying RAG-powered chatbots on AWS Bedrock, building multi-agent workflows with CrewAI, and designing LLM evaluation frameworks that catch hallucinations before they reach production. My focus is always the same: AI that works in the real world, not just the notebook.
Before that, at Royal Dutch Shell, I moved into data science — building predictive maintenance models that cut equipment downtime by 25% across oil refineries, and forecasting dashboards that saved 10% of budget allocations across five geographies. That's where I fell in love with the gap between a working model and a working solution.
I started my career at TCS testing point-of-sale systems, spending a year in the UK guiding offshore teams through complex software rollouts. Those early years taught me how enterprise systems break under real conditions — a foundation that still shapes how I build today.
Value I Bring
What I Can Solve
Scalable RAG pipelines
Design and ship hybrid retrieval systems (BM25 + dense vectors + reranker) that process 100K+ multimodal documents with 90%+ accuracy in production.
Agentic AI workflows
Architect multi-agent systems with CrewAI and LangGraph — tool-augmented, guardrailed, and evaluated with Ragas before they touch production.
LLM evaluation frameworks
Build frameworks that measure faithfulness, relevancy, hallucination, toxicity, and bias — so model upgrades don't silently degrade your product.
Research → production AI
Take proof-of-concept LLM experiments and harden them: containerise, add CI/CD gates, instrument with latency and drift monitoring on AWS.
AWS Bedrock & GenAI infra
Deploy secure, cost-efficient GenAI systems using Bedrock, Textract, OpenSearch, and Step Functions — with CloudWatch observability built in.
ML-driven business outcomes
Translate messy enterprise data into XGBoost, Random Forest, or deep-learning models that move real metrics: 30% fewer maintenance incidents, 10% budget saved.
Expertise
Technical Skills
Generative AI
LLM Frameworks & APIs
MLOps
Cloud (AWS)
Core ML & Data
Career
Work Experience
Senior Data Scientist
May 2022 – PresentBritish Telecom (BT) · London, UK
- ▸Deployed RAG-powered chatbot using LLMs + AWS Bedrock, reducing manual data extraction time by 70%
- ▸Built multi-agent agentic workflows with CrewAI for batch processing with hallucination guardrails
- ▸Designed LLM evaluation framework using Ragas — faithfulness, relevancy, bias, and hallucination detection
- ▸Processed 100K+ multimodal documents with 90%+ accuracy using AWS Textract + OpenSearch
- ▸Engineered recommendation models (XGBoost + market basket analysis) increasing VAS sales by 30%
Data Scientist
Sep 2016 – May 2022Royal Dutch Shell · Netherlands / Remote
- ▸Built predictive maintenance models (XGBoost, Random Forests) cutting maintenance costs by 30% and unplanned downtime by 25%
- ▸Developed Power BI forecasting dashboard for materials on-time delivery across 5 geographies, saving 10% budget
- ▸Applied NLP, clustering, and statistical inference across large datasets using PySpark and SparkSQL
IT Analyst
Dec 2010 – Aug 2016Tata Consultancy Services (TCS) · India / UK
- ▸Led System Integration Testing & UAT to validate client PoS systems at enterprise scale
- ▸Spent one year in the UK guiding offshore teams through new PoS software implementation
- ▸Worked with card and payment systems, PCI standards, and ISO 8583 protocols
Work
Featured Projects
Production-Grade RAG Evaluation Pipeline
- ›Hybrid retrieval — BM25 sparse + contextual dense search — fed through a Cohere reranker
- ›Citation enforcement grounds every answer in source documents; no hallucinated references
- ›Prompts version-controlled in a config file — every change is tracked and reproducible
- ›Offline RAGAS script measures faithfulness, answer relevancy, and context precision
- ›GitHub Actions gate runs eval on every PR; merge blocked if any metric drops below threshold
Outcome: Quality regressions caught at PR stage, not in production. Stack: LangChain/LangGraph, Chroma vector store, Cohere reranker — every retrieval step traceable, every prompt change auditable.
AI-Powered Resume Parser
- ›PDF → structured JSON pipeline: pdfplumber extracts text → Llama 3.3 70B parses via Fireworks AI
- ›JSON schema enforcement: instructor library constrains LLM output to an exact Pydantic v2 model
- ›Retry mechanism: catches invalid outputs, re-prompts the LLM once, then fails gracefully — no silent errors
- ›Split-view UI: original PDF alongside experience timeline, color-coded skill tags, and education cards
- ›One-click JSON export, dark/light mode, drag-and-drop upload with animated progress steps
Outcome: Live on Fly.io. Structured output guaranteed at the schema level — retry logic and graceful failure handle the edge cases that plain prompting misses.
Local AI Assistant using Ollama
- ›Runs Phi-3 Mini, Mistral 7B, and LLaMA 3.2 fully on-device via Ollama — no cloud calls
- ›FastAPI backend for offline operation with structured JSON outputs
- ›Pydantic validation and retry logic ensure consistent, well-formed responses
- ›Benchmarked all three models across speed, accuracy, and resource trade-offs
Outcome: Rigorous benchmark published on Dev.to — documented which model wins for which use case on consumer hardware.
Academic
Education
2023 – 2025
Liverpool John Moores UniversityM.S. Machine Learning & Artificial Intelligence
Liverpool, UK
2022 – 2023
IIIT BangaloreExecutive PG in Data Science & AI
Bangalore, India
Statistics & Probability · ML · NLP · Neural Networks · MLOps
2006 – 2010
New Horizon College of EngineeringB.E. Electronics & Communication
Bangalore, India
Visvesvaraya Technological University
Get in Touch
Let's Connect
Open to senior data science and AI engineering roles. If you're building something ambitious with LLMs or agentic systems, I'd love to talk.