Skip to content
View SangiSI's full-sized avatar
🎯
Focusing
🎯
Focusing

Block or report SangiSI

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 supported. This note will be visible to only you.
Report abuse

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

Report abuse
SangiSI/README.md

Hi there! I'm Sangam 👋

Visitors

I'm an Applied Data Scientist, deeply passionate about advancing Artificial Intelligence. My work focuses on Geometric Deep Learning, Advanced Statistical Learning, Large Language Models (LLMs), and MLOps, with an emphasis on applied research, production AI systems, and decision intelligence.


🔍 What I do

  • 🔭 Working on Applied AI Research and productifying AI prototypes
  • 🌱 Exploring Agentic and Generative AI, including LLM-powered decision support, multi-agent systems, and human-in-the-loop AI
  • 🤝 Open to collaboration across academia and industry in the AI/ML space
  • 🧠 Experienced in designing and operationalizing ML pipelines and MLOps workflows with reproducibility, monitoring, and governance in mind
  • 🧪 Interested in LLM evaluation, bias analysis, and robustness for real-world analytical and research workflows
  • 💬 Open to conversations on anything - always happy to connect and exchange ideas!
  • ⚡ Fun fact: Built a graph model to identify influencers - surprisingly, the quietest node was the most connected

🚀 Featured Work

  • LLM Model Selection Lab
    Decision-centric evaluation lab for intelligent LLM model selection across real-world GenAI workflows.

  • Databricks MLOps Lifecycle
    End-to-end ML lifecycle using Spark ML, MLflow, Delta Lake, orchestration, and drift monitoring.

  • pgvector Semantic Search Demo
    Vector similarity search system using PostgreSQL pgvector for semantic retrieval and RAG-style workflows.

  • Time Series Research Lab
    Forecasting, anomaly detection, and statistical modelling for large-scale temporal data analysis.


🔭 Current Research Directions

My interests sit at the intersection of Applied AI systems, MLOps, and decision intelligence.

Current focus areas include:

  • Agentic AI architectures and multi-agent decision systems
  • Evaluation, reliability, and robustness of large language models in analytical workflows
  • AI-driven decision intelligence platforms for complex operational environments
  • Scalable ML systems and reproducible experimentation

🛠 My Skills


🔬 Engineering & Quality


🌍 Where to find me

LinkedIn GitHub Outlook Email Gmail


Pinned Loading

  1. llm-model-selection-lab llm-model-selection-lab Public

    Decision-centric evaluation lab for intelligent LLM model selection using GitHub Models. Benchmarks task performance, system behavior, and trade-offs (latency, consistency, schema adherence) for re…

    Python 1

  2. pgvector-semantic-search-demo pgvector-semantic-search-demo Public

    End-to-end semantic search implementation using PostgreSQL + pgvector, demonstrating embedding pipelines, vector indexing, and scalable retrieval workflows for RAG-style applications.

    Python 2

  3. databricks-mlops-lifecycle-interactive databricks-mlops-lifecycle-interactive Public

    Production-grade Databricks MLOps lifecycle demonstrating Spark ML pipelines, MLflow experiment tracking, Delta Lake feature storage, orchestration, and model drift monitoring.

    Python 1

  4. timeseries-research-lab timeseries-research-lab Public

    Applied time-series forecasting and anomaly detection using ML and statistical baselines, with rigorous experimentation, residual-driven diagnostics, and reproducible evaluation workflows.

    Jupyter Notebook 1

  5. llm-foundations-and-systems llm-foundations-and-systems Public

    Structured repository covering LLM foundations, fine-tuning workflows, optimization strategies, deployment patterns, evaluation methods, and Responsible AI considerations.

    Jupyter Notebook 2

  6. analytics-sql-patterns-for-ai-systems analytics-sql-patterns-for-ai-systems Public

    Business-oriented SQL patterns for KPI analytics, customer behavior modeling, anomaly detection, and decision-support workflows.

    1