AI Engineer with less than a year in RAG and AI Engineering
AI is analyzing your overall score…
Identifying your key strengths…
Evaluating your skill match against the job requirements…
Assessing your cultural and operational fit
Final-year Computer Science (Data Science) student with hands-on experience developing Retrieval-Augmented Generation (RAG) applications, FastAPI backends, and LLM evaluation pipelines through academic projects and an AI internship. Interested in AI engineering and backend development, with a focus on building reliable, secure, and practical AI solutions while continuously learning modern GenAI technologies.
New Horizon College of Engineering, VTU, Bengaluru
B.E. · Computer Science (Data Science)
August 1, 2022 – June 30, 2026
Edutainer, PAT Technologies
AI Engineer Intern
January 1, 2026 – April 1, 2026
Bengaluru, Karnataka, India
SecureRAG
June 1, 2025 – Present
Built a secure Retrieval-Augmented Generation (RAG) application using FastAPI, LangChain, ChromaDB, PostgreSQL, and React. Implemented document ingestion, embedding generation, vector search, and response generation over internal documents. Added PII masking and prompt validation to improve response safety. Built an evaluation pipeline using Faithfulness, Context Precision, Context Recall, and Hallucination Detection metrics to compare retrieval quality across iterations. Structured the backend into modular components for retrieval, security, and LLM interaction.
LLM Evaluation Framework
June 1, 2025 – Present
Built a framework to compare GPT-4, LLaMA-2, and Mistral on the same evaluation set. Evaluated model responses with and without retrieval context to measure the impact of RAG on factual accuracy. Observed improved factual accuracy after introducing retrieval context. On the selected benchmark, Mistral-7B delivered performance comparable to GPT-4 on factual questions while remaining a lower-cost inference option. Structured the code so adding a new model only requires writing one adapter class, with no changes to the evaluation logic itself.
View ProjectCityscape AI
June 1, 2025 – Present
Built a platform where citizens report environmental issues in their locality. Developed a Random Forest model that aggregates citizen reports into locality-wise health scores and highlights critical zones on an interactive map. Handled the backend (FastAPI), ML pipeline (feature engineering, stratified split, weighted F1 scoring), and report aggregation logic, working in a team of four. Used Git for version control and collaborated with teammates through feature-based branch development. Accepted for publication at IEEE ICUIS 2025 after peer review. The proposed approach achieved 87% agreement with official government sensor data across the evaluation dataset.
Advanced RAG & LLM Applications
Udemy
January 1, 2025 – Present
IEEE Data Science Workshop
IEEE
January 1, 2023 – Present
Cultural Fit Analysis
The candidate's project diversity, including a civic tech project (Cityscape AI) and a focus on secure and evaluated AI solutions, suggests an interest in impactful and responsible AI development. The academic publication and continuous learning through certifications align with a growth-oriented culture. The target role of AI Engineer aligns well with the candidate's demonstrated skills and project focus.
Soft Skills & Operational Fit
The candidate demonstrates good collaboration skills through team projects and version control usage (Git). The ability to structure code for modularity (LLM Evaluation Framework, SecureRAG) suggests good software engineering practices. The internship experience shows an ability to integrate tools into daily workflows and iterate based on feedback, indicating a practical, problem-solving mindset.