N
Neel Shah
Available for AI/LLM consulting

Neel Shah
AI Engineer
& Researcher

10+ years building data systems and AI. Now specialising in LLM deployment, Claude & GPT integrations, and AI-ready data engineering. Based in Ottawa, Canada.

Claude API Local LLMs NLP Data Engineering Healthcare Informatics Open Source
About me View résumé Get in touch
1M+
Downloads
10+
Years exp.
89+
Citations
Expertise

What I build

From LLM pipelines to health data infrastructure — I work at the frontier of AI and real-world data systems.

🤖
LLM Engineering
Claude API, GPT/Codex integrations, prompt engineering, RAG pipelines, vector databases
🏠
Local LLM Deployment
Ollama, LM Studio, llama.cpp — running models privately on-prem or edge devices
📦
AI-Ready Data
Curating, labelling, and structuring datasets for fine-tuning and RAG applications
🧠
NLP & ML
Text classification, sentiment analysis, social media mining, Random Forest & ensemble methods
🏥
Healthcare Informatics
National health data pipelines at CIHI, population health analytics, public health research
⚙️
Data Engineering
Elasticsearch, Kibana, real-time distributed pipelines, large-scale Python processing
Focus Area

AI & LLM Ecosystem

🧡
Claude API
Anthropic
🌿
GPT / Codex
OpenAI
🦙
Ollama
Local LLMs
💻
LM Studio
On-device AI
Services

AI consulting & implementation

I help teams integrate LLMs into production — from selecting the right model to building retrieval-augmented pipelines, generating AI-ready training data, and deploying local models for privacy-sensitive workloads.

Discuss a project
LLM integration & API wrappers
RAG pipeline design
Local / on-prem LLM setup
AI-ready dataset curation
Prompt engineering
Model evaluation & benchmarking
Fine-tuning preparation
Health data AI pipelines
Published Work

Research

All papers
3
Papers
89+
Total citations
64
Most cited
2020 25 citations

Assessing Canadians Health Activity and Nutritional Habits Through Social Media

Frontiers in Public Health
✦ 93.4% accuracy · Random Forest
NLPPublic HealthML
2018 64 citations

A framework for social media data analytics using Elasticsearch and Kibana

Wireless Networks · Springer
✦ 64 citations · Most cited
ElasticsearchBig Data
2019

The analysis of Canada's health through social media using machine learning

Conference Paper
✦ Health ML · Canada
MLSocial Media
Open Source

Projects & Contributions

All projects
😊 emot Python

Emoji & emoticon detection library. An early open source achievement that grew to 1M+ downloads globally.

⭐ 196 🍴 79 1M+ downloads
📊 Arxiv Analysis Jupyter

Analysis of 24,000+ research papers mapping AI/ML trends over time. Full dataset included.

⭐ 4 24K+ papers
🔬 Scopus India Dataset

Data analysis of Indian researchers in Scopus journals (2000–2016) with full dataset published.

📌 Pinned 2000–2016

Let's build something together

Looking for expertise in LLM deployment, AI data pipelines, or data engineering? Let's connect.

Send me an email LinkedIn