Harsha Vardhan Chintamaneni
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
Work Experience
- 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.
- 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
- 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.
- 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.
- 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
Certifications
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.
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- Free Job BoardFree
Verified jobs, posted in the last 3 days
verified openings crawled ATS-by-ATS from 115,000+ real company career pages across 54 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 - Resume Writing ServicesFrom $25.99
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 - Drivetube OneFrom $39.99 / 3 mo
Daily matched jobs, tailored resumes, or we apply for you
Drivetube's paid service. Community sends daily Jobsheets of fresh jobs matched to your profile on WhatsApp and email, with the Drivetube Community ($39.99 for 3 months or $69.99 for 6 months; ₹999 or ₹1,899 in India). Jobhunt is one-time application credits with Community included: one credit tailors one resume and its cover letter (100 for $99 with 3 months of Community, 250 for $199 with 6 months). Let Us Apply is an add-on to Jobhunt: a human expert applies 250 times for you on your credits ($0.60 each, $150). Everything lives on one dashboard at drivetube.ai/drivetubeone.
Documentation - Drivetube HireFree tier
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.