
AI Engineer with less than a year in Deep Learning and RAG architectures
AI is analyzing your overall score…
Identifying your key strengths…
Evaluating your skill match against the job requirements…
Assessing your cultural and operational fit
M.Tech AI/ML candidate at VIT Chennai with hands-on experience in developing and implementing AI algorithms, models, and systems. Proficient in Python, PyTorch, and TensorFlow with a strong foundation in deep learning, NLP, and RAG architectures. Experienced in collaborating with cross-functional teams to integrate AI solutions into real-world systems. Passionate about innovation and continuous learning in the field of artificial intelligence.
Vellore Institute of Technology (VIT)
M.Tech · Computer Science & Engineering (Artificial Intelligence & ML)
August 1, 2024 – Present
SRM Institute of Science & Technology
B.Tech · Computer Science & Engineering
August 1, 2017 – June 30, 2021
L&T Edutech
Agentic AI Intern
February 1, 2026 – May 31, 2026
India
Xyma Analytics
Software Engineer Trainee
May 1, 2022 – August 31, 2022
Chennai, Tamil Nadu, India
L&T Construction – (Internship project)AI Interview Platform
February 1, 2026 – May 31, 2026
Built an Agentic AI recruitment platform at L&T Edutech using LangGraph for dynamic multi-path interview routing that adapts in real time based on candidate responses. Conducted research and analysis to evaluate LLM performance across multiple interview scenarios, informing model selection and prompt engineering decisions. Developed a RAG pipeline using ChromaDB and Llama 3.3 (Groq) to generate resume-aware, role-specific technical questions - eliminating generic interviewing. Engineered an automated Evaluation Engine that cross-references candidate answers with Job Descriptions, improving candidate-role matching accuracy by 15%.
Air Cracks Detection using Deep Learning modules
September 1, 2025 – June 1, 2026
Built a Real-Time Crack Detection System using YOLOv8 and EfficientNetB0 for automated crack localization and severity classification (crack/non-crack) in structural images. Integrated Grad-CAM explainability and Groq LLM safety report generation with PDF export and Gmail alerts for critical crack detections. Deployed as an end-to-end Streamlit web application, integrating AI-powered crack detection into an accessible user interface for structural safety monitoring.
Parkinson's Disease Prediction
May 1, 2025 – June 1, 2026
Developed ML classification models on UK Biobank genetic and lifestyle data for early Parkinson's diagnosis, achieving 91% accuracy using Random Forest Classifier. Conducted feature engineering, cross-validation, and model evaluation; deployed as an interactive Streamlit web app.
Introduction to Generative AI
Google Cloud Skills Boost
June 1, 2026 – Present
Introduction to Cloud Computing
NPTEL
June 1, 2026 – Present
Cultural Fit Analysis
The candidate's project diversity, ranging from structural safety monitoring to AI recruitment platforms and disease prediction, indicates a broad interest in applying AI across different domains. Their academic background (M.Tech in AI/ML) and professional experience (Agentic AI Intern) align well with an AI Engineer role, demonstrating a clear career path towards AI. The breadth of technical skills listed, including various AI/ML frameworks, programming languages, and MLOps tools, suggests adaptability and a willingness to explore different technologies. This indicates a good cultural fit for an innovative and continuously learning environment.
Soft Skills & Operational Fit
The candidate demonstrates a proactive approach to learning and applying new technologies, as seen in their pursuit of an M.Tech in AI/ML and various certifications. Their project descriptions indicate an ability to work on complex problems and integrate AI solutions into user-facing applications. Collaboration with cross-functional teams is mentioned, suggesting an understanding of team dynamics. However, the provided data does not offer specific insights into stress handling, detailed communication styles, or direct team collaboration effectiveness beyond project descriptions.