Hey, I'm Sumit.

I specialize in solution architecture and solutions engineering in the data and AI space. As a Sr. Solution Engineer at Snowflake, I've helped Fortune 50 customers in healthcare and finance deploy data and AI solutions at scale.

I enjoy being the technical relationship owner who strategizes with customer execs, brainstorms with engineers, owns the outcome, and stays on it until it's live.

I'm a builder at heart and love building new things in my free time. This reminds me I do need to cut down on my AI spend 😞

If you've read this far, say hello. I'd love to chat if you'd like to collaborate.

Sumit
Side projects

Things I built outside work

Here are some of the weekend projects I built and run in my free time. With today's AI tools anyone can build. I believe what separates an average builder from a good one is ease of use, design taste and whether it solves a real problem.

CrazySound.ai

↗

Generates short audio ads, phone greetings and dubs from a text description. Writes the script, picks a voice, adds music and exports WAV or MP3. Pay per job, no subscription.

InsureHunt.com

↗

Matches people with local insurance agents across nine lines of insurance. Also has guides, county-level home insurance cost data, and a tool that audits an agent’s website and Google Business Profile.

CantonFairSourcing.com

↗

A sourcing service for buyers at the Canton Fair in Guangzhou. A product catalog with landed-cost estimates, plus supplier checks, quotes and order handling by a team on the ground.
Visual guides

Visual Guides on Snowflake, Data & More

All visual guides →
Cortex AI, inside Snowflake LLMs, search and text-to-SQL that run where the data already lives Your data tables · docs · PDFs tickets · call notes Snowflake Cortex LLM functions COMPLETE · SUMMARIZE TRANSLATE · SENTIMENT CLASSIFY · EXTRACT Cortex Search hybrid vector + keyword the "R" in RAG auto-refreshes with data Cortex Analyst question → SQL guided by a semantic model you define Document AI pull fields out of invoices, forms, scans into columns Cortex Agents plan → Search or Analyst → run tools → answer with citations one API for chat apps, Slack bots, Snowflake Intelligence Call it from ▸ plain SQL ▸ Python / Snowpark ▸ REST API ▸ Streamlit apps ▸ Snowflake Intelligence Models hosted in-platform Anthropic · OpenAI · Meta · Mistral no keys, no egress, billed in credits Data never leaves the governance boundary RBAC, masking policies, row access and lineage apply to AI calls too sketch 01 · snowflake, drawn out
AI

What Cortex is and how I use it

The parts of Snowflake Cortex I actually reach for, and how a RAG app fits together without moving data out.
Adaptive Warehouses Set a spend ceiling. Snowflake picks the compute for each query. Before one warehouse per workload XS BI dashboards M ELT jobs 2XL "the month-end one" idle 27 days a month queued ✗ you pick the size up front ✗ resize by hand when it queues ✗ idle time = credits burned ✗ one big query jams the small one same SQL After one adaptive warehouse ADAPTIVE_WH q1 small q2 big, briefly q3 medium ✓ Snowflake sizes compute per query ✓ scales out when queries queue ✓ shared pool, so far less idle you set: max credits that's the whole config What stays the same connection strings keep the warehouse name, roles and grants carry over, queries are unchanged. start with dev and BI; leave tuned ELT on classic warehouses at first sketch 02 · snowflake, drawn out
Compute

Adaptive warehouses, and what changes when you switch

Snowflake can now size and scale compute per query. What changes, what stays the same, and how I'd move a customer over.
Where do Snowflake credits go? Six things I check, and the queries I use to find them compute ~ 3 of every 4 credits typical mix, yours will differ virtual warehouses (running, and idle) storage: tables + Time Travel + Fail-safe cloud services + serverless (tasks, search, Cortex) Six things I check, in order 1 Auto-suspend at 60s, not 10 minutes cache loss is cheaper than paying for silence · AUTO_SUSPEND = 60 2 Find the top 10 queries, fix those first QUERY_ATTRIBUTION_HISTORY · a few queries burn most of the credits 3 Right-size: start small, grow only on spill each size up doubles cost; bytes spilled to remote storage is your signal 4 Put guardrails on: monitors, budgets, timeouts RESOURCE MONITOR · BUDGET · STATEMENT_TIMEOUT on every warehouse 5 Trim storage you never read transient tables for staging · Time Travel 1 day, not 90 · drop the clones nobody owns 6 Consolidate warehouses, then go adaptive fewer, busier warehouses idle less · adaptive warehouses do the sizing for you Rule of thumb: 20% of warehouses and queries cause 80% of the spend. sketch 03 · snowflake, drawn out
Cost

Six things I check when a Snowflake bill goes up

Where credits go, the six things I look at in order, and the queries I use to find them.
Cities I Have Lived
Gujarat, India grew up, graduated Bangalore 2004 Mumbai 2005 Raleigh, NC 2006 ✈ moved to the US Seattle 2008 Jacksonville, FL 2010 → now home since filter coffee first real winter (bought a coat) it rained. for two years. beach on weekdays
Contact

Get in touch

I'm interested in applied AI and forward-deployed engineering roles. Email is the best way to reach me.

LinkedIn GitHub