Skip to content

Harsha Vardhan Chintamaneni

Machine Learning Engineer • Arlington, TX • h*******************@gmail.com • +19******987 • linkedin.com/••••• • drivetube.ai/•••••

Professional Summary

Machine Learning Engineer with 4+ years of experience designing and deploying scalable AI/ML systems in production. Expertise in Python, PyTorch, TensorFlow, LLMs, RAG pipelines, and computer vision. Proven record building MLOps workflows on AWS using Docker and Kubernetes, improving model accuracy and reducing operational costs.

Technical Skills

Programming Language: Python,C++,SQL
Backend Technologies: FastAPI
Cloud Platforms: Amazon Web Services
Version Control & Development Tools: Git,Jupyter Notebook
DevOps & Infrastructure: Docker,Kubernetes
Testing & QA: PyTest
Data Analysis & Visualization: Pandas,NumPy,Matplotlib,SciPy,Tableau,Power BI,Plotly,VGG
Machine Learning & AI: Convolutional Neural Networks,Transformer,YOLO,Cross-Validation
AI/ML Frameworks & Libraries: PyTorch,TensorFlow,Keras,scikit-learn,XGBoost,ResNet,UNet,Hugging Face Transformers,spaCy,Pruning
Generative AI & LLMs: LangChain,OpenAI API,Quantization
Vector Databases & RAG: Retrieval-Augmented Generation
MLOps: MLflow,Feature Engineering,Experiment Tracking,Hyperparameter Tuning

Work Experience

KPMG
ML Engineer
Jun 2024 – Present
Delivered AI/ML solutions for insurance operations including underwriting, claims assessment, and customer analytics to improve automation and decision support.
Tech Stack: Python, TensorFlow, PyTorch, LangChain, OpenAI API, FAISS, FastAPI, Docker, Kubernetes, MLflow, AWS, S3, EC2, ResNet-50, VGG-16
  • Architected production ML pipelines in Python using TensorFlow and PyTorch for automated insurance risk assessment, processing 10,000+ monthly applications and reducing underwriting time by 40% while achieving 92% model accuracy.
  • Designed and deployed RAG workflows with LangChain, FAISS, and OpenAI API for intelligent document retrieval across insurance files, cutting retrieval latency by 45% and achieving 87% answer relevance on internal evaluations.
  • Built an internal LLM-powered chatbot as a FastAPI microservice, containerized with Docker, providing instant policy lookups and reducing manual policy lookup effort for support teams.
  • Developed a CNN-based damage assessment pipeline (ResNet-50, VGG-16) for claims triage that achieved 89% classification accuracy and accelerated claims processing by 35% across ~50,000 annual claims.
  • Optimized models through hyperparameter tuning, pruning and quantization to reduce inference latency by 60%, resulting in $25,000 in annual AWS cost savings while preserving accuracy.
  • Established MLOps CI/CD and monitoring using Docker, Kubernetes and MLflow; cut model deployment time from two weeks to three days and implemented model drift detection to maintain production reliability.
Cognizant
Data Scientist
Jan 2022 – Dec 2023
Built predictive analytics, forecasting and anomaly detection models for enterprise clients to improve retention, supply planning and fraud prevention; delivered BI reporting to stakeholders.
Tech Stack: Pandas, NumPy, SciPy, scikit-learn, XGBoost, SQL, Tableau, Power BI, LSTM, GRU, Isolation Forest
  • Developed customer churn models using Random Forest and XGBoost achieving 85% accuracy; contributed to an 18% reduction in churn and retained approximately $500K in annual revenue.
  • Built robust data preprocessing pipelines with Pandas, NumPy and SciPy to clean and transform 5M+ monthly records; feature engineering improved model performance by 22%.
  • Implemented LSTM and GRU time-series forecasting for demand across 200+ SKUs achieving ~80% accuracy, reducing stockouts by 25% and lowering overstock by 20%.
  • Conducted anomaly detection using K-Means, DBSCAN and Isolation Forest to identify fraudulent transactions at a 95% detection rate, helping prevent ~$300K in losses.
  • Performed exploratory data analysis and feature selection using correlation analysis and L1/L2 regularization to identify 12 critical features, increasing marketing campaign ROI by 28%.
  • Delivered Tableau and Power BI dashboards integrated with SQL for 15+ stakeholders, automating reports and saving ~30 manual reporting hours per month; prototyped Hugging Face models for text analytics.

Projects

Real-Time Dehazing & Object Detection Pipeline
Tools Used: ResNet-34, UNet, YOLO, CUDA, Computer Vision
  • Designed an end-to-end pipeline combining ResNet34-UNet for image dehazing and YOLO-based object detection, reducing false detection rate by ~40% under simulated fog.
  • Implemented a fog intensity estimation module using GLCM texture analysis with 98% correlation to ground-truth scattering, enabling adaptive preprocessing that improved YOLO mAP by 18%.
  • Optimized inference for low-latency GPU execution achieving real-time throughput (30+ FPS) suitable for autonomous vehicle and surveillance scenarios.
Multilingual Emotion & Sentiment Engine
Tools Used: BERT, Custom Transformers, Tokenization, CUDA
  • Built a multilingual sentiment and NER engine using fine-tuned BERT and custom transformer variants across 5+ languages, reaching 94.2% accuracy and 91.8% F1 on domain datasets.
  • Developed language-aware tokenization to lower out-of-vocabulary rates by 31% and improve cross-lingual transfer for low-resource languages.
  • Accelerated transformer inference using CUDA and dynamic batching to achieve 3x throughput and enable processing of 50,000+ documents per hour.
Intelligent Document Q&A System using RAG & LLMs
Tools Used: LangChain, FAISS, Hugging Face sentence-transformers, FastAPI, Docker
  • Architected a RAG pipeline using LangChain, FAISS and OpenAI GPT to support natural language queries over large unstructured corpora, achieving 87% answer relevance on custom benchmarks.
  • Implemented semantic chunking and sentence-transformer embeddings to reduce retrieval latency by 45% and improve context precision by 32% versus fixed-size chunking.
  • Deployed the system as a Dockerized FastAPI microservice supporting concurrent users with sub-2-second response times; validated across legal, financial and technical document sets.

Education

University of Texas at Arlington
M.S., Computer & Information Science • Arlington, TX • Jan 2024 – Dec 2025
Lovely Professional University
B.Tech, Computer Science & Engineering • Punjab, India • Jul 2019 – May 2023

Certifications

Azure AI Fundamentals — Microsoft
Python for Machine Learning and Data Science — Udemy
Machine Learning with Python: Decision Trees, Logistic Regression, Clustering — LinkedIn Learning
Python Programming — Microsoft
Data Analysis — Microsoft
AI Agents — Hugging Face
LangChain Essentials — LangChain Academy

Achievements

  • Image Restoration using Deep Learning Techniques: A Dataset Free Approach — 2023: Proceedings of ICCS 2023 Kilby 100, Lovely Professional University, Punjab, India.

Powered by Drivetube · Create your own profile at drivetube.ai

Everything on Drivetube

Six products, two of them free forever. Start wherever you are.

Read the docs →
  • Your free digital resume

    at drivetube.ai/in/your-name: one true standard resume with a Hiring Snapshot (visa status, expected salary, notice period, work preference, relocation), an ATS-ready PDF download and a single shareable link. Free forever; interview requests come from verified employers and your contact details stay masked until you accept.

    Documentation
  • Verified jobs, posted in the last 3 days

    verified openings crawled ATS-by-ATS from 100,000+ real company career pages across 35 ATS platforms. Shows the true posting date from the source ATS — not when a listing was indexed — and deletes every general listing 3 days after it was actually posted. No ghost jobs, no ad-sponsored listings, no staffing reposts, no account needed.

    Documentation
  • Job Hunt ProgramFrom $199.99

    We run your job hunt for you

    managed job hunting, a one-time purchase from $199.99. JobScout matches verified roles to your real experience band, Blend AI writes a uniquely tailored resume and cover letter for every application, and the Autofill extension fills the form — or Let Us Apply submits it for you.

    Documentation
  • Written by senior career writers

    human-written, ATS-optimised resumes by senior career writers, from ₹499.99 / $25.99. Available in every country, written to the destination country's own standard — a US resume, UK CV, German Lebenslauf and Indian resume are genuinely different documents. A paid service, separate from the free Drivetube Profile.

    Documentation
  • Community MembershipFrom $49.99/yr

    AI tools, gated filters and a $10,000+ library

    from $49.99/year (₹1,999/year in India), or $4.99/month in the iOS app. Unlocks the gated job-board filters — visa sponsorship, security clearance, workplace and application time — plus Job-Scout AI matching, Resume Report AI, Interview AI prep sheets, Recruiter Outreach AI sent from your own Gmail, Apply or Skip triage, a daily market feed and a $10,000+ library including 23 ATS-validated resume templates.

    Documentation
  • For employers — no job postings, no applications

    hiring with no job postings and no applications. Paste your real job description and AI matches it against candidates' true standard resumes, returning ranked candidates with a match %, matched and missing skills and written reasoning. Free tier included; employers pay, candidates never do.

    Documentation
  • Documentation

    every product explained in full, with feature-by-feature comparisons against the job boards, AI apply tools, resume services and hiring platforms people actually use.

  • Playbooks

    tactical job-search guides. Each post is one named tactic with the situation it applies to, the exact steps, a copy-paste message and honest failure modes. Free, no account.

The job board covers the United States, India, United Kingdom, Canada, Europe and Australia, and Resume Writing Services are available in every country.

Pricing is identical on the web, iOS and Android — no app-store markup. Monthly Community membership is purchased in the iOS app only; the website sells annual plans. The Android app has no in-app purchase, so Android members subscribe on drivetube.ai and then sign in to the app with full access. Membership follows your account, not your device.