Open to new opportunities

Agentic AI
Developer

Building multi-agent systems, RAG pipelines, and geospatial automation workflows with Python. Based in India — available remotely.

Education

Academic background
PG-Diploma in GenAI & Agentic AI
IIT Roorkee · Online
2025 – 26
Masters in Geo-Informatics
Savitribai Phule Pune University · Pune
2022 – 24
Bachelor of Science
RTM Nagpur University · Nagpur
2019 – 22

Expertise

Tools & domains

AI & Data

RAGMulti-Agent SystemsLLM Fine-tuningPrompt EngineeringEDAML Pipelines

Geospatial

GIS AutomationRemote SensingGeoPandasRasterioQGISArcGIS Pro

Frameworks

LangChainLangGraphCrewAIAutoGenOllamaMLflowPyTorchScikit-learn

Tooling

Git / GitHubPostgreSQLPowerBIPandasNumPyMatplotlib

Career

Work experience
Cartographer
NielsenIQ · GIS & Data
July 2024 – Present
  • Georeferencing and boundary creation for multi-country data frames.
  • Automated GIS tasks with Python to process and analyse vector data at scale.
  • Built PyQGIS & GeoPandas scripts to clean, validate, and modify shapefiles.
  • Data validation and quality checks to maintain error-free boundary maps.
  • Automated merging, attribute updates, and geometry corrections from multiple sources.
Python Mentor
Self-employed · Weekend Cohorts
Project-based
  • Python training for data & GIS professionals (Pandas, Matplotlib, Scikit-learn).
  • Mentored 4+ batches (3–4 months each) on automation and data processing.
  • Designed hands-on exercises and workflow optimisation solutions.

Projects

Selected work
02
GeoAI Assistant — Dynamic Geospatial Query Engine

AI-powered system to query any geospatial dataset (GeoJSON, SHP, KML) using natural language. Uses LLM tool-calling instead of plain RAG — no hardcoded schema — with multi-step execution, interactive PyDeck maps, and a built-in EDA dashboard.

PythonGeoPandasOllamaLLM Tool-CallingStreamlitPyDeck
03
MAS Fitness & Diet Planner

Multi-agent system for personalised fitness and diet planning — user profiling, RAG, expert agents, and automated PDF report generation via ReportLab.

LangGraphRAGCrewAIReportLab
04
Geospatial Data Automation Pipeline

High-performance pipeline converting large shapefiles into structured KML outputs using GeoPandas + Shapely, with multiprocessing and custom XML formatting.

GeoPandasShapelyMultiprocessingKML
05
Satellite Image Classification — Supervised

Land cover classification with SVM, Random Forest, Decision Tree, and XGBoost. Full preprocessing, feature engineering, accuracy metrics, and classification maps.

Scikit-learnXGBoostRemote Sensing
06
Satellite Image Classification — Unsupervised

Unsupervised pipeline for Sentinel-2B imagery using K-Means + PCA. Clustering evaluation and visual insights for coastal land analysis.

K-MeansPCASentinel-2B
07
Flood Prediction Model

Logistic regression model for flood risk — preprocessing, training, evaluation, and visualisations to identify high-risk zones.

Logistic RegressionScikit-learnGeospatial
08
Automated NDVI for Sentinel Imagery

Automation pipeline to compute NDVI from Sentinel imagery (.img, .tiff) with Rasterio and NumPy. Outputs GeoTIFFs for scalable vegetation health monitoring.

RasterioNumPyNDVIGeoTIFF