AI Engineer with less than a year in NLP and RAG
AI is analyzing your overall score…
Identifying your key strengths…
Evaluating your skill match against the job requirements…
Assessing your cultural and operational fit
Aspiring Machine Learning Engineer with strong foundations in data science, statistics, and Python programming. Hands-on experience building AI-powered applications using NLP, Retrieval-Augmented Generation (RAG), and deep learning. Seeking an entry-level role to apply analytical skills and contribute to real-world AI solutions.
Balaji Institute of Technology and Science
B.Tech · Mechanical Engineering
N/A – June 30, 2024
Cognifyz Technologies
Data Scientist Intern
April 1, 2025 – May 1, 2025
India
Infotact Solutions
Data Scientist Intern
April 1, 2025 – June 1, 2025
Bengaluru, Karnataka, India
RAG-Based Intelligent Q&A System
June 1, 2026 – Present
Designed Retrieval-Augmented Generation pipeline using LangChain and Hugging Face. Integrated ChromaDB for semantic vector search, improving response accuracy and speed. Developed Streamlit UI for interactive, real-time question answering. Reduced hallucinations by improving context relevance and retrieval quality.
Text Generation using LSTM
June 1, 2026 – Present
Built character-level text generation model using LSTM neural networks. Implemented end-to-end pipeline: data preprocessing, model training, and inference. Generated coherent text using temperature-based sampling techniques.
Data Science (Basic to Advanced) Certification
SETWIN
June 1, 2026 – Present
Data Science Training
Quality Thoughts
June 1, 2026 – Present
Cultural Fit Analysis
The candidate's projects and internships are well-aligned with an AI Engineer role, demonstrating a clear interest and foundational skill set in the field. The diversity of projects (RAG, text generation) shows a breadth of interest within AI/ML. However, the experience level is entry-level, which might require more mentorship and integration into a senior team.
Soft Skills & Operational Fit
The candidate's project descriptions indicate a problem-solving approach, particularly in reducing hallucinations in RAG systems and improving classification accuracy. The internship experiences suggest an ability to work within defined project scopes. However, without direct interview data, assessing collaboration, stress handling, and communication clarity in a team setting is limited.