graph by datavruti
mygraph.id/juhidwivedi

Juhi Dwivedi

Data Engineer

Gurgaon, HaryanaBuilding since Jun 2024 (2+ yrs)
LinkedInGitHub
Headline

My path threads together computer vision deployment, recommendation systems, and backend API ownership, consistently landing on the automation layer that removes manual or repetitive work for others.

2.51Inference Latency (p95)

ms latency

98%YOLOv11 Model Accuracy (mAP@50)
1M+TruthIn App Users Served
Featured in Times of Indiaoral cancer screening CNN article
Represented Roles

Specialized Functions & Roles.

Engineering capabilities and specialized roles demonstrated across real production work.

Data Engineer

Primary Role

Machine Learning Engineer

AI Engineer

MLOps Engineer

Backend Engineer

Signals

Live in Production.

Each signal ties back to a specific, evidenced moment.

Built

4 moments

Systems shipped end-to-end, from schema to deploy.

  • •Published IEEE paper on CNN-based analysis of PCG signals
  • •Built Automation Fixer to cut manual QA root-cause work by ~80%
  • •Built a recommendation system with OpenAI embeddings and XGBoost

Learned

2 moments

New tools and depth picked up on the job.

  • •Published AI pathology research with Taylor & Francis
  • •Experimenting with RAG and context grounding

Solved

1 moment

Gaps closed - false positives, edge cases, dead ends.

  • •Fixed a priority-client production OOM in the journal search service

Scaled

1 moment

Taken from prototype to real production volume.

  • •Deployed a YOLOv11 auto-cropping model to TruthIn's 1M+ user base
Growth trajectory

Juhi's career, mapped.

A timeline of milestones captured directly from real work.

  1. Started applying AI to scientific imaging

  2. Took ownership of ML pipelines in production

  3. Built a recommendation system end to end

  4. Moved into backend systems at scale

  5. Resolved a production memory incident

  6. Started building internal AI tooling

Stack

Daily tools.

What Juhi actually reaches for, pulled from the tags attached to captured moments.

Work

Key Work By Role

What they built, shipped and owned at each role, with impact numbers where there are any.

AlgoSec

Development Engineer · Oct 2025 - Oct 2026

Fixed a priority-client production OOM in the journal search service

Diagnosed and fixed an out-of-memory issue for a priority client in /journal/v1/overview/search by introducing batched retrieval in Metro Facade, bounding per-request memory for large result sets.

Batched retrieval over 500+ recordsNo recurrence since the fix shippedResolved a production OOM issue in the journal search service that had affected a priority client for around 2 months.
Stack:JavaKafkaREST APIsProduction Debugging
View case study

Built Automation Fixer to cut manual QA root-cause work by ~80%

Built Automation Fixer, a tool that automates QA root-cause analysis and PR generation, and an Ollama/n8n RAG assistant over internal code and docs to support the Support team.

~80% faster QA root-cause analysis and PR generation20% fewer developer escalations via the RAG assistant
Stack:Ollaman8nRAGAutomationLLM
View case study

More from this role

  • Developed REST APIs in ACE Network Analyzer Core (MS-Metro, Metro Facade API layer, Device Manager), the backend computing Journal change history and risks for ACE Network Analyzer; Kafka pub/sub between the two.
  • Migrated NAC services from Java 11 to 17, fixing library and inter-service compatibility issues.
  • Sanity-tested 7 releases (Dev, Stage, Production) via CI/CD on Kubernetes; reviewed 45% of team PRs.

Natfirst Pvt. Ltd.

Data Engineer · Feb 2025 - Sep 2025

Deployed a YOLOv11 auto-cropping model to TruthIn's 1M+ user base

Deployed a YOLOv11 auto-cropping model achieving 98% mAP@50 at 2.51 ms latency for TruthIn, an Android app with 1M+ users.

98% mAP@502.51 ms inference latencyServing 1M+ users on Android
Stack:YOLOv11Computer VisionAndroidModel Deployment
View case study

Built a recommendation system with OpenAI embeddings and XGBoost

Built a recommendation system combining OpenAI embeddings and XGBoost, reaching 95.73% Top-1 and 99.02% Top-5 accuracy, alongside an agentic evaluation workflow using LangChain, LangGraph, and CrewAI.

95.73% Top-1 accuracy99.02% Top-5 accuracy
Stack:OpenAI EmbeddingsXGBoostLangChainLangGraphCrewAI
View case study

Independently built and deployed StudyBuddy, a full-stack AI tutor grounded in uploaded PDFs

Independently built and deployed StudyBuddy, a full-stack AI tutor that answers only from uploaded PDFs with page-level citations and adaptive exams, using an Express 5 REST API with an OpenAPI contract generating Zod validation and typed hooks.

Full-stack build across React 19, TypeScript, Node.js/Express, and PostgreSQL
Stack:ReactTypeScriptNode.jsPostgreSQLGemini
View case study

More from this role

  • Built a scalable ETL pipeline on AWS SageMaker, EC2 and S3 for automated training and model versioning (Docker).

IRDE, DRDO

Research Intern · Jun 2024 - Jan 2025
  • Built a Flask app automating aberration correction in hyperspectral images, cutting manual processing by 95%.
  • Led data annotation and preprocessing (Label Studio) for an AI landmine-detection initiative with IIT Hyderabad.
Outside Work

Side projects, open source & publications.

Independent builds, open-source contributions, technical writing, and experiments beyond the day job.

Side project

StudyBuddy

Independently built and deployed a full-stack AI tutor answering only from uploaded PDFs, with page-level citations and adaptive exams; Express 5 REST API with an OpenAPI contract generating Zod validation and typed hooks. Benchmarked 5 vision models (Gemini Flash, Qwen2.5-VL 3B/7B, Gemma 3 12B) for PDF page reading: hosted Gemini was 7-30x faster per page (6.9 s vs 46-209 s) than local open-weight models; built a 72-item eval set.

Side project

Sushrut Samitah

Built an IoT + AI system integrating an electronic stethoscope with a CNN inference pipeline (preprocessing, MFCC extraction, live prediction) for real-time cardiac condition classification, achieving 94% accuracy.

Side project

Mukta

Developed a multimodal AI-assisted oral cancer screening system, using the patented Oral Cancer Detection Device, combining CNN-based image classification (91% accuracy) and parametric analysis.

Experiment

RAG Experimentation

Experimenting with retrieval-augmented generation (RAG) techniques, including context grounding.

Experiment

Sustainable AI Research

Researching sustainable AI as an area of ongoing study.

Side project

Deep Learning for Cardiovascular Health: CNN-Based Automated Analysis of PCG Signals

Authored a peer-reviewed paper on using CNN-based deep learning to automatically analyze phonocardiogram signals for cardiovascular health assessment, published with IEEE.

Learning

Formal record.

  • M.Tech. (CS&E)
    Indian Institute of Technology, Patna
    2025 - Present
  • B.Tech. (CS&E, Hons: AI & ML)
    Amity University UP
    2021 - 2025
  • Cisco® CCNAv7
    Cisco
  • Scrum Fundamentals (SFC™)
  • SQL
    HackerRank
  • GitHub Foundations
    GitHub
  • Claude 101
Verified tools

Numbers straight from the source.

Pulled directly from connected accounts, so the work speaks for itself.

LeetCode

solved
644
medium
323
hard
81
contest rating
1,823

Profile last updated 6 days ago.

Liked Juhi's graph?

Build yours today.

Start with your resume