Skip to content
View codebygarrysingh's full-sized avatar

Block or report codebygarrysingh

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
codebygarrysingh/README.md

Garry Singh — Principal AI & Data Engineer

MSc Software Engineering (AI/ML) · Oxford · PMP · CSM

I help financial institutions and enterprise teams ship production AI systems that actually work at scale — LLMOps, RAG pipelines, multi-agent architectures, and the data platforms that power them.

📍 Toronto, ON · Available for consulting & senior contract engagements · Remote-first

LinkedIn Email Portfolio


What I Do

Domain Focus
🤖 AI / LLM Engineering Production LLM systems, RAG pipelines, multi-agent architectures (LangChain, LangGraph), LLMOps
🗄️ Data Platform Architecture Lakehouse design, real-time streaming (Kafka, Spark), Snowflake, Delta Lake, Databricks
☁️ Cloud & MLOps Azure AKS, AWS SageMaker/Bedrock, Kubernetes, Terraform, MLflow, drift detection
🏛️ Technical Advisory Architecture reviews, engineering team leadership, technical due diligence

Tech Stack

Languages

Python Java SQL Scala TypeScript

AI / ML

LangChain OpenAI TensorFlow PyTorch MLflow

Data

Apache Kafka Apache Spark Snowflake Databricks

Cloud

Azure AWS Kubernetes Terraform


Selected Work

Multi-agent AI system patterns for financial services: compliance intelligence, risk monitoring, and regulatory automation. LangGraph supervisor architecture with human-in-the-loop escalation.

Enterprise-grade RAG with hybrid search (dense + BM25 + RRF), RAGAS evaluation framework, Redis semantic caching, and Guardrails AI output validation.

End-to-end LLMOps: experiment tracking, model registry, drift detection, A/B testing, and automated CI/CD quality gates for production LLM systems.

Enterprise streaming platform: Kafka exactly-once delivery, Spark Structured Streaming, Delta Lake medallion architecture, and Great Expectations data quality.

LSTM time-series forecasting, multi-class classification, and deep learning for IoT sensor data using PyTorch and TensorFlow.


By the Numbers

  • 60% reduction in manual processing — multi-agent compliance AI (production)
  • 80% faster regulatory reporting — distributed batch system redesign at Tier-1 bank
  • 10M+ daily events processed — real-time market risk streaming platform
  • <10ms latency — capital markets Kafka migration, 5M+ daily transactions
  • 10+ years across Canada's top financial institutions, global asset managers, and government platforms

Certifications

  • 🎓 MSc Software Engineering (AI/ML) — University of Oxford
  • ☁️ Azure AI Engineer Associate — Microsoft
  • ☁️ Azure Data Engineer Associate — Microsoft
  • 📐 Machine Learning Specialization — Stanford / Andrew Ng
  • 📋 PMP — PMI · CSM — Scrum Alliance

Let's Work Together

Available for consulting engagements and senior contract roles — remote-first, based in Toronto.

📅 Book a free consultation · 📧 Email me · 🌐 Portfolio

Pinned Loading

  1. ml-neural-network-projects ml-neural-network-projects Public

    This repository is a collection of machine learning projects that leverage the power of neural networks. From predicting room occupancy using sensor data to tackling various real-world challenges, …

    Jupyter Notebook

  2. data-prep-utility data-prep-utility Public

    The quality of your data is crucial for the success of a machine learning models and data integration. This is a data preprocessing/prep utility that performs data checks and preprocessing steps es…

    Python 1

  3. ml-regression-python-projects ml-regression-python-projects Public

    This collection features practical implementations of use cases, guiding you through the process of building, training, and evaluating regression models and advanced model fine tuning techniques.

    Jupyter Notebook 3

  4. ml-algorithms-projects ml-algorithms-projects Public

    Repository contains Jupiter notebooks covering work on advanced machine learning algorithms covering artificial neural networks using TensorFlow.

    Jupyter Notebook 1

  5. ml-classification-projects ml-classification-projects Public

    These notebooks guide cover the entire process, of building, training, and evaluating classification models effectively and includes advanced model fine tuning techniques.

    Jupyter Notebook 2

  6. blog-summarizer-app blog-summarizer-app Public

    Implementation of a common real-world application of Large Language Models (LLM) & Generative AI. Powered by Python and the OpenAI’s GPT-3 model, this app embeds AI generated summaries into blogs.

    Python 3 1