AI Engineer @ J&J

Hi 👋, I’m

Vamsi Krishna Vipparla

From pixels and language to systems people can use.

I’m an AI/ML engineer working across computer vision, intelligent document workflows and applied AI. My work connects medical-device label inspection, manufacturing vision, conversational tools and research on 3D medical images.

Computer vision · Applied AI · Research

ENGINEERING CAPABILITIES

Research fluency.
Production instinct.

I take AI from experiment to deployment. I build and evaluate models, connect them to the services people use, and use operator feedback and delivery traces to improve the workflow.

End-to-end ownership

From prototype
to production.

  1. Design & prototype
  2. Train & evaluate
  3. Deploy & operate
  4. Trace & improve

01 / Deployed systems

Production AI & deployment

I led ASTRA’s OCR upgrade and contributed to the AWS migration. The workflow connects label capture and extraction to operator review, inspection storage and background delivery. Delivery tracking helps distinguish a saved inspection from a record successfully received downstream.

PythonPaddleOCRFastAPIAWS

02 / Applied AI engineering

Agentic AI & LLM systems

QuoteMaster’s prototype searches the approved catalog, queues room previews and generates estimates from confirmed inputs. The agent workflow under development adds persistent state, human confirmation and retry handling. Catalog IDs and pricing rules stay in application logic.

PythonDjangoLangGraph (planned)OpenCV

03 / Retrieval and evidence

Retrieval & knowledge systems

I work on retrieval where the source matters. QuoteMaster retrieves from approved catalog and FAQ text. In ASTRA, extracted fields lead back to their source image, so operators can inspect the evidence for a value before confirming it.

Catalog and FAQ retrievaldocument OCRevidence mapping

04 / Research to implementation

Computer vision & applied research

I work across industrial inspection and medical imaging. Inspect AI compares a work area against a known-clear reference and highlights changes for review. My published lung-nodule research tests multi-scale 3D context, attention and model fusion for reducing false-positive candidates.

OpenCVResNetPyTorch3D CNNs

HOW I BUILDfour habits, grounded in the work

Keep the evidence close

A predicted label field is more useful when an operator can see the image region behind it. In ASTRA, extraction and review belong in the same workflow.

Measure the right boundary

Inference time, end-to-end latency and operator time answer different questions. I keep the dataset, measurement and limits beside each result.

Design around the person

Line clearance remains an operator decision. Vision highlights changes, and feedback helps refine the next inspection.

Connect research to implementation

My lung-nodule work uses local and surrounding 3D context to reduce false-positive candidates. It also taught me to make evaluation splits and model fusion explicit.

PROJECTSselected systems and the evidence behind them

Illustrative ASTRA · Intelligent label verification emblem

ASTRA · Intelligent label verification

Package photos become extracted identifiers, barcode values and symbol detections that an operator can review against their visual source.

PaddleOCRPythoncomputer visionFastAPIAWS
Illustrative Inspect AI · Line clearance emblem

Inspect AI · Line clearance

A camera compares an inspection area with a known-clear reference and highlights changes for an operator to review before the next run.

PythonOpenCVstructural similarityResNet-18image embeddings
Illustrative QuoteMaster · From product questions to a draft quote emblem

QuoteMaster · From product questions to a draft quote

A design and quoting assistant connects approved product information, room previews and deterministic price calculations for curtains, blinds and related interior products.

DjangoPythonapproved-text retrievalOpenCV GrabCutimage-editing integration
Illustrative MP-AFNet · Lung-nodule false-positive reduction emblem

MP-AFNet · Lung-nodule false-positive reduction

Small nodules and surrounding anatomy can look similar in CT. Our research scores candidates from an upstream detector using both local detail and wider 3D context.

Illustrative Edge vision · Counting vehicles at a plant gate emblem

Edge vision · Counting vehicles at a plant gate

A Jetson Nano camera pipeline supplies an inbound vehicle count and supporting snapshot for comparison with RFID observations.

Jetson NanoYOLOv4-tinyFastMOTOpenCVedge-to-service integration
Illustrative Dealer self-service · Finance information in WhatsApp emblem

Dealer self-service · Finance information in WhatsApp

Mahindra dealers can request finance information, including outstanding balances, receipts and ageing reports, through a familiar messaging interface.

RasaInfobipFlaskRedisSQL Server

EXPERIENCEwhere I have worked, and what I built there

May 2025–Present
Johnson & Johnson

Johnson & Johnson · AI Engineer

May 2025–Present · United States · Client engagement

Computer vision and intelligent inspection work across medical-device label verification, line clearance, annotation and PPE prototypes. Led the ASTRA OCR upgrade and worked on migration and downstream record reconciliation.

June 2024–April 2025
BlueVerse

BlueVerse · Software Engineer, AI/ML

June 2024–April 2025 · United States

Worked on AI/ML software and product workflows. The QuoteMaster case study presents the currently documented prototype and its agentic development roadmap separately.

August 2020–May 2022
Mahindra Rise

Mahindra Rise · Assistant Manager, Emerging Technology, AI/ML

August 2020–May 2022 · India

Developed computer vision and language-understanding components for vehicle tracking, plate recognition, industrial inspection, camera-based monitoring and dealer self-service.

August 2019–July 2020
Mahindra Rise

Mahindra Rise · Graduate Engineer

August 2019–July 2020 · India

Worked on manufacturing vision, including tractor decal detection and sealant segmentation.

January–May 2019
BML Munjal University

BML Munjal University · Research Assistant

January–May 2019 · India

Developed multi-scale, attention-based 3D CNN methods for lung-nodule candidate classification in low-dose CT.

RESEARCHpublished work, with traceable impact

Attention Based Multi-Patched 3D-CNNs with Hybrid Fusion Architecture for Reducing False Positives during Lung Nodule Detection

Vamsi Krishna Vipparla, Premith Kumar Chilukuri and Giri Babu Kande. Journal of Computer and Communications, 9(4), 1–26, 2021. DOI: 10.4236/jcc.2021.94001.

The work investigates how multi-scale 3D context, attention and model agreement can reduce false positives among lung-nodule candidates. The paper reports 0.931 CPM on LUNA16.

5 indexed citations, checked November 15, 2026 in OpenAlex, Semantic Scholar and Crossref. Citation counts depend on the index and can change. Citations indicate scholarly use; they do not establish clinical adoption.

Publisher · DOI · Citation record

MORE WORKexplore the full project archive

Mahindra · project archive

Teams · Business workflows

Business questions and actions become cards and task modules inside Microsoft Teams.

Microsoft TeamsAzure BotAdaptive CardsNode.jsReact
Mahindra · project archive

Phone sensor acquisition

A phone becomes a source of three-axis accelerometer readings for a local visualization.

PythonSensorDroidSensor callbacks
Mahindra

ANPR · Gate-camera plate recognition

Motion-triggered vehicle detection isolates high-resolution plate images for OCR and gate records.

YOLOOpenCVGoogle Cloud VisionFlaskMySQL
Mahindra · project archive

Antyodaya · PDF table ingestion

State documents move through discovery, download, table extraction and database preparation.

PythonTabulaDockerPDF extraction
Mahindra · project archive

Basebot · HR conversational services

Employee questions route to policies, FAQ retrieval or HR actions within a modular chatbot.

RasaDjangoFastAPIRedisWhooshGensim
Mahindra

Tractor decal verification

Locate the tractor and decal region before checking model-identifying text on both sides.

YOLOv3-tinyOpenCV DNNOCR
Mahindra · project archive

Engine test analytics

A dashboard connects test measurements with parameter definitions and tolerance limits.

Data extractionAnalytics APIsDashboards
Mahindra

Face localization API

A still-image service returns face boxes and confidence scores for downstream processing.

OpenCV DNNCaffe SSDFlask
Mahindra

Face-mask detection

A two-class detector identifies faces and mask status from an uploaded image.

YOLO tinyOpenCV DNNFlask
Mahindra

ArcFace · Face recognition

Enrollment and recognition use face embeddings within a subscription-scoped gallery.

ArcFaceRetinaFaceFlaskMongoDBDocker
Mahindra · project archive

Interactive camera demo

A desktop event prototype renders face detections and classifier outputs from a camera feed.

OpenCVMTCNNTkinterPython
Mahindra · project archive

Supplier allocation planning

Demand, supplier mappings and logistics costs feed a transportation allocation workflow.

PythonFlaskOperations researchSQL
Mahindra · project archive

PAN card extraction

Card localization reduces unrelated page text before OCR and structured-field parsing.

YOLOFastAPIGoogle Cloud VisionPDF processing
Mahindra · project archive

Partner API request signing

A compact integration turns a serialized request into an HMAC authorization header.

PythonHMAC SHA-256REST
Mahindra · project archive

Sajhedaari · Multilingual voice workflow

Speech and text questions route through language understanding, FAQ retrieval and custom actions.

RasaDjangoSpeech interfacesDocker
Mahindra

Sealant bead inspection

Inspect visible sealant continuity and highlight suspect regions before assembly.

OpenCVU-NetSSIMImage registration
Mahindra

Camera geometry · Proximity monitoring

Person detection and calibrated ground-plane geometry turn fixed-camera views into proximity indicators.

YOLOv5mHomographyOpenCVFlaskDBSCAN
Mahindra · project archive

SOP viewer · Scan to procedure

A QR code connects a work location with its procedure PDF in an Android viewer.

AndroidJavaPythonAmazon S3QR codes
Mahindra · project archive

Genie · Employee-service API adapter

A Django adapter reshapes upstream employee-service data for a Teams application.

DjangoRESTGoogle App Engine
Mahindra · project archive

International Knowledge Portal

A reader portal and separate CMS make company and country information accessible and maintainable.

ReactDjango RESTMySQLCeleryRedis
Mahindra · project archive

Asynchronous invoice extraction

Uploaded invoices pass through template or QR processing before structured results are returned.

invoice2dataGoogle Cloud StoragePub/SubDatastoreDocker
BML Munjal University · Research

Lung nodule research · PyTorch implementation

An implementation of multi-scale attention CNNs makes candidate scoring and FROC evaluation explicit.

PyTorch3D CNNsAttentionLUNA16FROC
Mahindra · project archive

Robin · Interactive PDF conversion

A desktop workflow flattens interactive PDFs for downstream processing while retaining originals.

Robin RPAAdobe PDFWindows Task Scheduler
Mahindra · project archive

MSolve · Guided desktop remedies

Verified support procedures become signed desktop tools offered through an employee-support workflow.

PowerShellPS2EXECloud FunctionsDatastore
Mahindra · project archive

Vehicle telemetry delivery

A portal turns a vehicle, date range and parameter selection into a downloadable CSV.

ParquetBigQueryCloud StorageDatastoreApp Engine
Mahindra · project archive

MWatcher · Website health monitoring

Regional probes monitor website health alongside certificate and domain expiry.

AWS LambdaAmazon SQSMonitoringAlerting
Mahindra · project archive

Supplier test-certificate extraction

Certificate images and QR regions become structured records for supplier and admin portals.

Google Cloud Visioninvoice2dataPub/SubDatastorepyzbar
Mahindra · project archive

Visiting-card contact extraction

A card image becomes structured contact fields through provider and local OCR alternatives.

FlaskMicrosoft Form RecognizerTesseractAddress parsing
Johnson & Johnson · client engagement

CVAT + SAM · Interactive annotation

Promptable segmentation proposes editable masks while annotators retain control of the labels.

CVATSAMNuclioDjangoPostgreSQLDocker
Johnson & Johnson · client engagement

Gowning · Visual PPE inspection

Reference matching and garment-specific checks display visible PPE evidence for review.

SAMResNet50MTCNNYOLOStreamlit
Mahindra

Tractor chain and tyre alignment

Object detection supports inspection of chain and tyre alignment on industrial tractors.

UltralyticsObject detectionComputer vision

TOOLKITtools I have worked with

Computer vision

PyTorchTensorFlowOpenCVYOLOSAMPaddleOCR3D CNNstracking and image segmentation

Language and AI applications

RasaOpenAI APIsLangChainretrieval workflows and agent design

Engineering

PythonFastAPIFlaskDjangoDockerGitKubernetesAWSGCPAzure

Data

SQLPostgreSQLSQL ServerMySQLMongoDBNeo4j

EDUCATION & CREDENTIALS

Alibaba Cloud Tianchi Hackathon

3rd finalist across all campus teams

Built an NLP model for short text classification with limited training data.

Hackathon page

ACHIEVEMENTS

IDC DX Summit · Special Award for Resiliency

Issued by IDC (International Data Corporation) · Associated with Mahindra Group.

Recognized Mahindra Group’s end-to-end Back to Workplace solution, developed in-house on an open-source platform during the COVID-19 pandemic.

IDC Future Enterprise Awards

AICTE · Resource person

All India Council for Technical Education sponsored training at VVIT.

Taught machine learning and industry trends to faculty and students across campus, with examples from IT and automotive applications.

Prodigy–GradRight Merit Scholarship

Merit-based scholarship supporting my master’s in computer science at Arizona State University.

GradRight scholarships

Vamsi’s GradRight scholarship testimonial about pursuing a master’s at Arizona State University

Undergraduate scholarship

100% merit-based scholarship during my computer science degree at BML Munjal University.

BLOG

Weekly notes on computer vision, AI engineering, and lessons from building systems.

Browse the blog ↗

ABOUTthe path that connects the work

My path began with medical-imaging research and continued through automotive manufacturing, AI/ML software and medical-device inspection. I enjoy problems where models have to work with physical constraints, incomplete inputs and real operational handoffs.

I bring experience in Python, model development and system integration, and I’m interested in roles that connect computer vision and agentic AI with useful, measurable products.

LET’S CONNECT

If you’re building applied AI, computer vision or ML systems, I’d like to hear about the problem your team is working on.

Email me · LinkedIn · GitHub · Résumé (DOCX)

✳ Portfolio / Vamsi
portfolio / overview.md
✳

Explore the work.

Ask about my projects, research or experience. I’ll find the relevant evidence in this portfolio.

Free AI for questions · curated sections use no AI
PROJECT / FIELD NOTES