✢ not a portfolio — an agent-driven profile of one engineer

I didn't write a CV.
I shipped the pipeline that answers for me.

not a résumé

A résumé is a static string a human has to parse, trust, and re-read. It goes stale the day it's written, and it flatters. Every portfolio site is the same document with better kerning.

a data product

So this one is built the way I build everything else: one YAML file as the warehouse, a folder of skill files as the agent fleet, and a FastAPI service serving both. Query it instead.

Answers, not adjectivesEvery claim here resolves to a record you can fetch at /api/profile.
Grounded, not generatedThe fleet answers from skill files. Nothing is improvised at runtime.
More like codeEdit the YAML, redeploy, done. No CMS, no external services, no env vars.
agent — grounded on profile.yamlAgent 1.1
suresh@agent:~$
clock1.1
—
--:--:--
IST · UTC+5:30 · Hyderabad
glider1.1
Game of Life · still running
✢ 01

Career, rendered as a DAG

agent ▸ trace(career.pipeline)
Sep 2026 → present
full-time · remote

Head of Data Engineering RUNNING

Firmable · AI-powered sales intelligence

Owns Firmable's data: where it comes from, where it lives, whether it's right, and how it ships.

Nov 2022 → Aug 2026
full-time · remote

Founding Engineer SUCCESS

Firmable · AI-powered sales intelligence

First hire; architected the AI data stack and built the team.

2020 → 2023
three tasks, one scheduler

The parallel years ∥ CONCURRENT

Data Fusion Labs · Import.io · Accord Property Services
  • CEO, Data Fusion Labs (2020-23): ran a news-as-a-service platform for enterprise clients
  • Enterprise Solutions Architect, Import.io (2020-22): data architectures at 2 trillion+ records monthly
  • Back End Developer, Accord (2022-23): secure, scalable AWS backends for a construction-tech platform
Apr 2018 → Jan 2023
4 yrs 10 mos

Principal Software Engineer SUCCESS

Dell Technologies

Architected cloud-native microservices and distributed data systems.

Jul 2011 → Apr 2018
6 yrs 10 mos

Technical Lead ← Programmer Analyst ← Trainee SUCCESS

Cognizant

Built crawlers powering job listings in Google's jobs experience.

✢ 02

Throughput

agent ▸ sum(career.records)
Billions of records.
Trillions of tokens.
*measured across 15 years of pipelines, not estimated (ask the fleet)
billionsrecords processed
trillionstokens through LLM pipelines
2T+/morecords architected @ Import.io
300K+/yranalyst hours saved @ Dell
15 yrsmaking the web queryable
resume.pdfthe old way
Two pages, one direction. Cost — six minutes of your attention
Latency — read once, skimmed twice
Answers — whatever I guessed you'd ask
suresh.prothis page
An API with a face. Cost — one YAML file
Latency — answers while you scroll
Answers — whatever you actually ask
✢ 03

Pretraining

agent ▸ fetch(education)
degree
B.Tech, Computer Science
school
Sreenidhi Institute of Science and Technology
years
2008-2011

// where the base model was trained.

✢ 04

How I operate

agent ▸ recall(principles)
get_it_doneGet the work done — the tool is an implementation detail. Python crawlers, AI agents, or a brand-new team: whatever ships the outcome.
zero_to_oneBuild from scratch. Startups, teams, and data stacks — from the first byte and the first hire.
evals_firstNever run an LLM pipeline blind. Evals before scale, always.
ai_nativeIf an agent can do it, an agent should. Humans do the judgment.
cost_per_inputUnit economics are first-class. Token-max the useful, cut the slop.
direct_commsTerse beats verbose. Ship fast, measure everything, say the thing.
✢ 05

The fleet

agent ▸ fleet.list()

Specialist agents, each defined by its own skill file. Activate one to interrogate it.

✢ 06

Interrogate the fleet

agent ▸ interrogate(fleet)
agent — pick a specialistConsole 1.1
# pick an agent, then a question. answers are baked into each skill file.
✢ 07

Book a slot

agent ▸ schedule(call)
calendar — the only contact APIBooking 1.1

Data platform architecture, LLM pipelines, AI-native teams — or just a good conversation. No email on this site; the calendar is the API.

calendly.com/sureshbpro ▸ DM on LinkedIn MCA director record