Yedoti Likithsai
Generative AI Engineer • l**************@gmail.com • 934****659 • linkedin.com/••••• • drivetube.ai/•••••
Professional Summary
Generative AI Engineer with 0 years of professional experience, combining academic training with internship and hands-on project work building multimodal and LLM-driven applications. Proficient in Python, TensorFlow, scikit-learn and CNNs for computer-vision model development and evaluation; practical experience deploying LLM-driven flows using OpenAI API and Ollama and applying prompt engineering to improve assistant relevancy. Built full-stack prototypes with React, Node.js and MongoDB, integrating external APIs such as Google Calendar and Twilio for notifications and automation. Worked on healthcare and IoT domains — developed a multimodal medical diagnosis assistant and a BLE-based heart-rate monitoring pipeline that produced real-time dashboards. Demonstrates end-to-end ownership from model training and validation to Streamlit demos, API integration, and automation pipelines using n8n and Git for version control.
Technical Skills
Programming Language: Python,Java
Frontend Technologies: React
Backend Technologies: Node.js,Express.js,Google Calendar API,Twilio
Databases: MongoDB,MySQL
Version Control & Development Tools: Git,Jupyter Notebook
Data Analysis & Visualization: Pandas,Streamlit
Machine Learning & AI: CNN
AI/ML Frameworks & Libraries: TensorFlow,scikit-learn,OpenCV,EfficientNet
Generative AI & LLMs: OpenAI API,Ollama,LLM
Work Experience
Katyayani Organics
AI Intern
Dec 2025 – Jan 2026
Worked at a consumer products company; developed AI-driven customer interaction workflows and automation to support marketing and product information assistance.
Tech Stack: OpenAI API, n8n, Python, Streamlit, Git
- Designed and implemented AI-driven chat workflows using OpenAI API and Python to automate product inquiries and FAQ responses.
- Developed n8n automation pipelines for scheduling and publishing social media content and for ingesting engagement events into downstream processes.
- Integrated LLM prompt templates and prompt-engineering techniques to increase response relevance for product recommendations and information retrieval.
- Tested and validated assistant responses by building Python validation scripts to flag low-confidence outputs and logged failures for iterative prompt refinements.
- Built a Streamlit prototype to demo product-information retrieval and LLM-assisted responses for stakeholder evaluation.
- Documented workflow deployment steps and maintained repositories in Git to enable repeatable rollouts and simple handoff to the marketing team.
Projects
AI Medical Assistant – Multimodal Diagnosis System
Tools Used: Python, TensorFlow, EfficientNet, Llama, Ollama, OpenCV, Streamlit, MySQL, Jupyter Notebook
- Built an EfficientNet-based CNN in TensorFlow to classify skin diseases and X-ray abnormalities; trained and validated the model in Jupyter Notebook to achieve 93% accuracy on the test set.
- Integrated Llama models via Ollama to perform symptom reasoning and generate patient-facing recommendations using structured prompts.
- Developed an OpenCV preprocessing pipeline to standardize and augment medical images before model inference.
- Implemented a Streamlit interface for clinicians to upload images and receive multimodal diagnostic insights in real time.
- Designed and implemented secure MySQL storage for structured patient metadata and query APIs to support analytics and audit trails.
TaskPing: AI-Powered Smart Task Manager
Tools Used: React.js, Node.js, Express.js, MongoDB, OpenAI API, Google Calendar API
- Implemented backend REST APIs in Node.js and Express.js to create, update and manage tasks and reminders with token-based authentication.
- Integrated OpenAI API to parse natural-language and voice inputs into structured tasks using prompt-engineering patterns.
- Connected Google Calendar API to automatically schedule parsed tasks and create calendar events for deadlines.
- Built a responsive React frontend that supports natural-language task entry and displays synchronized calendar events.
- Persisted user tasks and metadata in MongoDB and implemented server-side validation to ensure data integrity.
Real-Time Heart Rate Monitoring System
Tools Used: Python, BLE, Java, MongoDB Atlas, scikit-learn, Pandas, Twilio, React.js
- Engineered a Python-based BLE ingestion service to stream heart-rate data from wearable sensors into the backend for realtime processing.
- Built an Android BLE client in Java to collect sensor data and forward encrypted payloads to the backend ingestion endpoint.
- Stored time-series heart-rate metrics in MongoDB Atlas and designed schemas optimized for high-ingest rates.
- Trained anomaly-detection models using scikit-learn and Pandas to detect abnormal heart-rate patterns and generate alerts.
- Automated emergency SMS notifications using the Twilio API when the model detected critical events.
Education
Vellore Institute of Technology, Amaravati
Bachelor of Technology in Computer Science • Sep 2022 – May 2026
Certifications
MERN Full Stack — Ethnus
Oracle GenAI Professional — Oracle
MongoDB Associate Database Administrator — MongoDB
Oracle Data Science Professional — Oracle
Powered by Drivetube · Create your own profile at drivetube.ai
Explore Drivetube
- Drivetube Profile — 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 Board — 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 Program — 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.
- Resume Writing Services — 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 Membership — from $4.99/month (₹1,999/year in India). 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.
- Drivetube Hire — for employers — 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.
Full product documentation — every product explained, with feature-by-feature comparisons against the job boards, AI apply tools, resume services and hiring platforms people actually use.
The job board covers the United States, India, United Kingdom, Canada, Europe and Australia, and Resume Writing Services are available in every country.