Vihitha R
Professional Summary
AI/ML Engineer with 4+ years of experience developing machine learning, NLP, and Generative AI applications for consumer technology and enterprise financial environments. Experienced designing recommendation systems, Retrieval-Augmented Generation (RAG) platforms, predictive models and production-grade ML services using PyTorch, Hugging Face, LangChain and cloud MLOps on AWS, Azure and GCP.
Technical Skills
Work Experience
- Engineered personalized recommendation systems using PyTorch and BERT-based content embeddings with Neo4j graph signals and PostgreSQL metadata, increasing content discovery engagement by 18% across streaming services.
- Fine-tuned transformer models (RoBERTa, LLaMA) with Hugging Face Transformers and PyTorch for multilingual sentiment and intent classification, enabling language-aware personalization across global interaction datasets.
- Designed and deployed RAG-powered semantic search using LangChain and LlamaIndex on AWS SageMaker to support low-latency semantic retrieval and personalized content surfacing for media catalogs.
- Automated ETL and feature engineering pipelines with AWS Glue, Pandas and PySpark, reducing preprocessing time by 35% and improving model training throughput for large-scale interaction data.
- Introduced internal ML automation using code-generation tools to accelerate routine pipeline scripting and tooling, cutting engineering turnaround on recurring tasks and improving developer productivity.
- Optimized production inference pipelines through MLflow experiment tracking, hyperparameter tuning, CI/CD integration and AWS monitoring, improving inference efficiency and deployment reliability by 22%.
- Built and evaluated Scikit-learn and XGBoost models on policy and claims datasets to identify retention drivers and improve risk prediction, increasing model accuracy by 16%.
- Processed high-volume structured and unstructured insurance records using SQL, PySpark and Azure Synapse Analytics to feed underwriting models and enterprise reporting.
- Applied Azure AI Named Entity Recognition to extract financial and policy entities from documents, automating parts of document review and reducing manual extraction effort.
- Designed a regulatory compliance RAG pipeline using LangChain, ChromaDB and Azure AI Search for enterprise document indexing and cross-referencing of policy language, cutting manual lookup time by 30%.
- Implemented model monitoring and explainability using Azure Monitor and SHAP reports and integrated Azure DevOps CI/CD, reducing validation and deployment turnaround by 28%.
- Accelerated pipeline scripting and unit-test coverage using GitHub Copilot, shortening development cycles for validation jobs and automation scripts.
- Developed predictive analytics solutions using Scikit-learn and XGBoost to forecast customer behavior and operational trends, improving decision-making accuracy by 22% for enterprise reporting.
- Consolidated large-scale transactional and operational datasets from PostgreSQL, MongoDB and data warehouse environments to support forecasting and KPI analysis pipelines.
- Built classification and regression pipelines using Random Forests and SVM with feature engineering to strengthen customer segmentation and operational performance analysis.
- Migrated legacy reporting into automated ETL pipelines using AWS Glue, Pandas and SQL, reducing manual reporting effort by 40% across analytics teams.
- Configured MLflow, Docker and CI/CD pipelines to maintain model versioning and streamline deployments, improving release efficiency for enterprise ML applications.
- Delivered interactive BI dashboards with Power BI and Tableau to monitor operational metrics and accelerate reporting turnaround by 30% for cross-functional stakeholders.
Projects
- Built a Retrieval-Augmented Generation platform using LangChain for LLM orchestration and LlamaIndex for document indexing to enable contextual retrieval across enterprise documentation.
- Implemented semantic search and vector storage with Pinecone, used PostgreSQL for metadata and caching strategies to improve response relevance for internal knowledge queries.
- Containerized LLM workflows and tracked experiments using Docker and MLflow to support scalable deployment and monitoring of AI-powered search services.
- Designed a real-time recommendation engine using PyTorch with Neo4j graph modeling to personalize content ranking based on user interactions.
- Orchestrated streaming pipelines with AWS Kinesis and PySpark to process high-volume engagement events and update recommendations dynamically.
- Tuned collaborative filtering and ranking models with Optuna and Scikit-learn to improve click-through rate by 18% in prototype deployments.
- Engineered automated ML deployment workflows using MLflow, Docker and Kubernetes to streamline model versioning and container orchestration across clouds.
- Provisioned training and inference environments on GCP Vertex AI and implemented monitoring to reduce model degradation incidents and improve stability.
- Automated validation and CI/CD processes with Jenkins and pipeline scripts to accelerate reliable releases in multi-cloud environments.
Education
Certifications
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.