$ whoami
senior automation & ai systems engineer
remote-friendly — works with teams anywhere
$ cat intro.txt
I build systems that act on their own — browsers that navigate and decide, computer-vision models that catch what a human would miss, pipelines that turn manual, repetitive work into something that runs itself. ~7 years focused on automation and applied AI: designing autonomous agents, training and shipping models, and building the infrastructure that lets them run unsupervised.
$ tail -f systems.log --summary
$ ls -la capabilities/
AI & LLM Integration
AWS Bedrock (Nova Pro, Nemotron) for vision, extraction, and decision-making agents; Hugging Face models across text, image, audio, and video; a fine-tuned LLaMA with vector-database retrieval; Rasa and DialogFlow conversational systems; GPT-3.5 for structured generation.
Computer Vision & Machine Learning
CNN models for object and impact detection, trained in Keras/TensorFlow, converted to ONNX and CoreML for production and on-device inference. Benchmarked against ground truth, not just validation accuracy — including the domain-shift gap between training data and real sensor data.
Team Leadership & QA Tooling
Lead a team of annotators on a sports-tech client's ground-truth pipeline — and built the desktop tools they use every day (impactAnnotator, rangeAnnotator): per-user attribution, correction/verification workflows, and live physics feedback so a correction's effect is visible immediately instead of discovered downstream.
Cloud & Backend Infrastructure
AWS Lambda, DynamoDB, S3, SES, EC2, and ECR running a real production data pipeline end to end — ingest, process, align, score, report, alert. Flask and Express servers as the glue between browser automation, models, and storage.
Data Engineering at Scale
Structured extraction and deduplication pipelines across dozens of thousands of records — union-find merge logic, fingerprint-based dedup, incremental resume, and atomic writes with shrink-guards so a bad run can't silently destroy good data.
Browser Automation & Scraping
Playwright and Chrome extensions (Manifest V3) driving real, logged-in sessions — not APIs. Human-paced clicking, virtualized-list handling, session portability across machines, and recovery logic built from watching real automations fail and fixing the actual cause.
Mobile & On-Device AI
SwiftUI apps calling Bedrock directly from the device via Cognito temporary credentials — no backend server in the critical path — plus on-device WKWebView automation for the same tasks a server would otherwise drive.
$ ps aux --systems
# six systems, live or run to completion — not demos
[ok] Marketplace Negotiation Agent
Capture listing -> Vision model prices it -> Negotiates autonomously
A browser extension plus a local server drives an operator's own authenticated session on a large consumer marketplace: assesses item condition from photos, prices accordingly, then negotiates with sellers autonomously — with rate-limit detection and messaging guards built after real incidents, not speculative edge cases.
# runs continuously on a cloud instance, negotiating in parallel
[ok] Sports Capture Quality Control
Device upload -> Parameter + CNN checks -> AI fallback -> Annotated video
Two production AWS Lambdas validate every capture a device uploads: parameter checks, then CNN/ONNX visual verification (Bedrock Nemotron where no model was trained for the mode), then a rendered debug video for anyone reviewing the shot.
# 86% recall on range-mode ball-impact detection · ~16s avg render time
[ok] Launch Monitor ML Suite
Collect 1,218 exports -> Engineer features -> Train 3 models -> Ship to iOS
Scraped bulk sensor exports from a third-party sports launch-monitor portal, then trained neural nets that predict spin rate, spin axis, and club speed from the metrics that are easy to measure — shipped as CoreML models for on-device iOS inference.
# club speed error cut from 20.5 km/h (legacy) to 1.99 km/h
[ok] Tournament Data Agent
Discover pages -> AI extraction -> Read flyer images -> Merge & dedupe
An autonomous agent discovers charity sports-event pages across a tournament-management platform, decides for itself how far to navigate to reach rosters, extracts structured data with a vision-capable model, and reads promotional flyer images via OCR when the details were never real HTML text.
# 178 tournaments extracted end to end from unstructured event pages
[ok] Professional Network Automator
Browse leads -> Human-paced engagement -> Email alerting
Runs locally and on a cloud instance independently, working through a lead list on a professional network and engaging with the content worth engaging with — randomized human-like pacing, daily caps, and crash-alert email built in after the process silently went down more than once.
# 1,541 items tracked · 98.8% success rate
[ok] Web Scraping Fleet
Browser extension -> Local server -> Deduplicated dataset
Five independent scrapers, each a purpose-built Chrome extension paired with a local server: association-executive directories, a speaker marketplace, a member community feed, and a professional network — each with its own dedup and resume logic.
# 22,000+ profiles and posts collected across 5 platforms
$ cat archive/accubits-systems.log
# shipped 2019–2023 at accubits technologies, for real clients
[ok] Deep Listening
Surveys & uploads -> Multi-modal extraction -> Fine-tuned LLM -> Vector retrieval
A multi-modal information-extraction platform. Hugging Face models handled object detection, tag generation, and image description on images; translation and transcription on audio; both combined for video; summarization and keyword extraction on text. A fine-tuned LLaMA drove additional extraction and chat, backed by a vector database for retrieval.
# text, image, audio and video in one extraction pipeline
[ok] CipBot
WhatsApp -> Structured chat flow -> Client database -> Admin panel
An intelligent chatbot connecting Cipla's procurement team with its vendors, deployed on WhatsApp. A structured chat flow surfaced internal database records, with role-based options per user type and an admin panel for reviewing interactions and data traffic.
# built on Rasa, live on WhatsApp for a pharma procurement team
[ok] Trajectus IVR
Phone call -> Voice IVR -> Medical query handling
An IVR-based chatbot handling medical query calls, built on Google DialogFlow. Delivered as outsourced work for Computer Instruments (CI).
# voice-first, not text — a different failure surface entirely
[ok] Coglide — Cori & Gx
Inbound email -> Contact extraction -> Extension sync -> Marketing database
"Cori", an email service extracting contact details out of inbound mail, plus "Gx", a browser extension syncing data from diverse marketing websites into Coglide's own database. Also owned the data scraping and automation work across the product, and ran the research server that fed its marketing data.
# the earliest version of the scraping work that runs through everything since
[ok] Emotyx
Live CCTV -> Backend network -> Customer insights
Backend network structure for software extracting intelligent, actionable insights from real-time CCTV footage for customer understanding — built and deployed in Python, handling the managing and recording of the footage itself.
# real-time video in production, not batch analysis
[ok] Attendance Management System
Student records -> Python backend -> Image processing
Owned the entire back-end code structure for managing student and attendance records, and supported the AI development around its image processing.
# full backend ownership, end to end
[ok] Other Projects
A GPT-3.5 minutes-to-meeting generator that transcribed calls and wrote up the minutes. Shell tooling to verify API endpoint data and harden it against SQL injection, shipped as a Postman collection. A Selenium scraper collecting marketing data across multiple social networks. A back-end network for the Learning & Development team, and a scraping service for Talent Acquisition to surface new candidates. Plus the back-end and detection module for PPE (Personal Protective Equipment) kit detection.
# the long tail — smaller builds, same instinct
$ cat experience.log
Most recent
AsimovX
Accubits Technologies
Sree Chitra Thirunal College of Engineering
$ cat about-me.txt
Maybe I'm lazy — but that's exactly what made me automate everything. Most of what's on this page started as "this manual work is stupid, I could automate it" and turned into something that runs on its own. That's the part I enjoy: the moment a system stops needing me.
Based in Bangalore, India, working with teams anywhere.
Off the clock I read a lot, and I'm a fairly serious gamer. Mostly Dota 2, where I play as devilsnare — currently rank 4300 on the SEA leaderboards, which takes about as much stubbornness as debugging someone else's Selenium script at 2am. Same instinct, different arena: learn the system, find where it breaks, get better at it.
$ ls blog/
[post] How I Created My First Discord Bot Using JavaScript
A walkthrough of building a Discord bot from scratch in JavaScript — setting it up, wiring the event handlers, and getting it running.
$ whois govind
Available for new work
$ cat links/