soham dandapath

soham dandapath

Senior Data Scientist at C3 AI

Customer-facing data scientist. I turn fuzzy business problems into forecasting models that actually ship, like knowing how much to build before the orders arrive.

Nowrunning forecasting programs for a couple of large enterprises, and re-reading the diffusion papers.

I build AI systems that make it out of the notebook and into production, and I build things from scratch to understand how they really work.

01About

Mostly, I want to know how things actually work.

I'm a senior data scientist at C3 AI. My path ran through Singapore and New York before the Bay Area: a BE in Computer Science from NTU, a stretch of internships from Shopee to Seagate, then an MS at Columbia with a focus in machine learning. The constant across all of it has been a stubborn kind of curiosity, the sort where I'll re-implement an idea from scratch just to find out how it actually works.

These days that curiosity has a job. At C3 I sit with customers, translate a vague business problem into something a model can answer, and carry it all the way to production. That's mostly probabilistic time-series forecasting, with some RAG-based LLM systems along the way. I care about three things in particular: models you can interpret, deployments you can reproduce, and tooling that makes the next engineer's job easier.

02Work

What I've worked on.

Jan 2024 – now
Senior Data ScientistMay 2026 – Present
  • Customer-facing lead on our largest forecasting engagements, owning projects from problem definition to production
  • Lead demand forecasting for the server business unit at a leading semiconductor company
  • Previously led yield forecasting at the world's largest berry producer, generating ~$5M in annual value
  • Manage release for our forecasting packages and mentor data scientists across teams and projects
Data ScientistJan 2024 – Apr 2026
  • Led demand forecasting for the largest CPG company in Guatemala, generating $2.3M in annual impact
  • Built a RAG-based LLM system for low-latency, policy-compliant document retrieval across C3 AI's internal documentation
  • Built and owned DRIPP, an internal Python deployment toolchain that reduced deployments from hours to minutes
  • Owned MetaML, the internal orchestration tool for time-series deployments
  • Led release management for forecasting packages, enforcing coding and packaging standards across teams
2023
Data Science Intern · C3 AI

Shipped an out-of-the-box hierarchical forecasting and reconciliation system, using post-hoc MinT/ERM and intrinsic DeepVAR-Hierarchical approaches for cross-level coherence, and integrated probabilistic forecasts with Integrated Gradients explainability so the outputs were both uncertainty-aware and interpretable.

2022
Data Scientist · Charles & Keith

Built a tree-based sales forecasting model for seasonal planning, a 95%+ accuracy image-similarity engine for product matching, and an order-management web app that improved accuracy while cutting manufacturing costs and stockouts.

2020 - 21
Earlier internships · Shopee, Seagate, Outstrip, CogniAble

A run of hands-on ML and data work: optimizing Airflow/HDFS pipelines and a compression tool that cut storage by 90%+ at Shopee; neural-net and tree models to forecast hard-drive test time at Seagate; a React and Rails KPI dashboard at Outstrip; and a two-stream I3D action-recognition model on AWS SageMaker for early autism screening at CogniAble.

03Projects

Most of these began as “I don't really get this, let me build it.”

Diffusion ModelGenerative models · 2023

A from-scratch implementation and experimentation sandbox for denoising diffusion models in PyTorch - forward noising, the reverse denoiser, and the sampling loop, derived by hand.

Fair Image Generation of Minority GroupsCausal ML · Generative models · 2023

A research project asking whether a structural causal model in the latent space of a bidirectional GAN can disentangle protected attributes well enough to generate minority-group images that fix a biased training set.

Co-Authorship Networkmost-starredNetwork science · Data · 2021

A network-science study of academic collaboration built from real DBLP bibliographic data: graph construction, centrality, and community detection used to study how a department's research reputation grew over time.

all projects, with case studies →

04Education

Where the fundamentals came from.

2023 - 24
MS, Computer Science (Machine Learning)
2017 - 21
BE, Computer Science

05Contact

This page grows as I do, so it's never really finished. If something here resonates, my inbox is open.