Help & Supportcareers@gravityer.com
AI Engineer with less than a year in Machine Learning, NLP, and Embedded Systems.
AI is analyzing your overall score…
Identifying your key strengths…
Evaluating your skill match against the job requirements…
Assessing your cultural and operational fit
AI/ML - focused engineering undergraduate with hands on experience in end-to-end machine learning and NLP systems, including sentiment analysis, retrieval - augmented generation (RAG), and predictive modeling. Currently an AI/ML Intern at IIT Madras, working on agentic AI and autonomous intelligent systems. Proficient in Python and deep learning frameworks, with a strong ability to design data-driven solutions for real-world problems.
University of Peradeniya
B.Sc. Eng (Hons) · Electrical & Electronics Engineering
August 1, 2022 – June 30, 2026
KN/Pallai Central College
GCE Advanced Level · Physical Science
N/A – May 31, 2020
IIT Madras
AI/ML Intern – Data Science & AI Department
April 1, 2026 – Present
India
CosIntR Pvt Ltd
Volunteer
October 1, 2025 – March 1, 2026
India
Audio-to-Text Sentiment Classifier
December 1, 2025 – Present
Multimodal sentiment analysis pipeline converting speech to text and predicting sentiment. Integrates NLP preprocessing with LSTM-based classification. Built an end-to-end pipeline for audio-to-text conversion and sentiment classification Implemented normalization, tokenization, stemming, and lemmatization Trained an LSTM model and evaluated using accuracy, ROC, and F1-score
View ProjectRAG-Based Document Question Answering System
November 1, 2025 – January 1, 2026
AI system enabling natural language queries over Sri Lankan tax documents using RAG. Retrieves accurate, source-cited answers in near real-time. Contributions: Built an end-to-end RAG pipeline with FAISS vector indexing and source-cited responses Assisted in building a FastAPI backend with dynamic PDF ingestion and live vector store updates Filtered retrieved sources to show only relevant document references per query Achieved <100ms retrieval latency and 1-2s end-to-end response time via Groq's LPU inference
View ProjectSmart Sensor Network for Structural Health Monitoring
April 1, 2025 – Present
FYP Research- Initial crack localization is carried out using image processing, followed by deployment of a custom capacitive sensor network for continuous crack monitoring and visualization. Contributions: Assisted in developing image processing algorithms for crack localization Designed a capacitive sensor and collected combining capacitance measurements with DHT11 data. Trained and optimized ML models through hyperparameter tuning and comparative evaluation
View ProjectSelected for publication at ICSBE 2025 - Smart Sensor Network for Structural Health Monitoring
ICSBE
January 1, 2025 – Present
iPURSE 2025: Shared findings and refined real-time structural prediction models
Unknown
January 1, 2025 – Present
EngEX 2025: Demonstrated IoT SHM with ESP32-CAM crack detection and visualization.
Unknown
January 1, 2025 – Present
ICSBE 2025: Presented smart crack detection system using ML, sensor data, and image processing.
Unknown
January 1, 2025 – Present
Cultural Fit Analysis
The candidate's academic background in Electrical & Electronics Engineering, coupled with diverse AI/ML projects (RAG, sentiment analysis, structural health monitoring), indicates a broad interest and adaptability. Their volunteer experience at CosIntR Pvt Ltd and current internship at IIT Madras show a willingness to contribute to real-world problems and engage with advanced AI concepts. The academic nature of most projects and the current student status suggest a strong learning orientation, which is beneficial for cultural fit in an evolving AI landscape. However, the limited professional experience outside of internships and volunteer work might require a team that can provide mentorship and structured growth opportunities.
Soft Skills & Operational Fit
The candidate demonstrates a proactive and collaborative approach through volunteer work and group projects. Their involvement in research presentations and publications indicates a drive for continuous learning and sharing knowledge. The ability to work on end-to-end solutions, from data acquisition to deployment, suggests good operational fit for practical AI engineering roles.