Shubhanshu Bishwash
Generative AI · Geospatial Systems · Climate Intelligence
Seasoned AI & Geospatial Engineer with deep expertise in Generative AI, Machine Learning, and Satellite Data Processing. Architecting autonomous multi-agent workflows, deploying Vision Transformers, and building no-touch AI pipelines that transform terabytes of raw Earth observation data into actionable climate intelligence for global enterprises.
Agentic AI & LLM Toolchain
Local LLMs (LLaMA), MCP servers, multi-agent orchestration, no-touch AI pipelines, and enterprise inference interfaces. Building autonomous data collection and validation workflows that run end-to-end without human intervention.
ML & Simulation
Time-series forecasting, climate risk, ESG scoring, and forward-looking analytics at institutional scale. Bayesian inference for uncertainty quantification across asset classes, Monte Carlo stress testing.
Geospatial Technology
Earth observation, DEM/SAR fusion, multi-temporal analytics, cloud-native geospatial on AWS/GCP. Processing terabytes of Sentinel, Landsat, MODIS, and VIIRS data for climate risk and urban analytics.
Climate Risk & ESG Analytics
Automating climate risk analisys via satallite and other sources. Physical risk exposure, emissions trajectories, TCFD and EU Taxonomy alignment.
Agentic Climate Risk Intelligence System
Multi-agent RAG pipeline ingesting 100k+ climate datasets (ERA5, CMIP6, Sentinel-2 LULC) into a vector store for natural language querying of physical risk scores. Bayesian inference for uncertainty quantification, LLM agents for autonomous ESG data validation, Monte Carlo stress testing for derivatives desk positioning.
Satellite-Based Exploration Platform
In-house geospatial application built for a geo-exploration division, replacing drone/on-site surveys with open-source satellite data to track vegetation regrowth and oil slicks. Vision Transformer models achieving 92%+ accuracy on multi-spectral imagery across 400+ reclamation sites.
Automated GIS Pipeline — NYU Stern
Automated GIS pipeline using Python, GDAL, and PostGIS for NYU Stern's Project Mumbai, saving 1,200+ manual hours/year. GANs for legacy satellite imagery enhancement (1997+) for remote road detection. Cloud-native flood risk analysis with Monte Carlo simulations on GCP.