Help & Supportcareers@gravityer.com
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 Engineer with less than a year in RAG Systems & NLP
Final-year Computer Science undergraduate with hands-on experience building AI/ML and Retrieval-Augmented Generation (RAG) systems using Python, LLMs (Llama 3.1 via Groq API), LangChain, and vector databases (FAISS, ChromaDB). Strong foundation in Data Structures & Algorithms, with practical exposure to NLP, hybrid search, and applied machine learning pipelines. Comfortable working close to the metal - implementing core logic from scratch rather than relying purely on high-level abstractions - and translating research-style ideas into deployable, end-to-end applications.
University of Engineering & Management
Bachelor of Technology · Computer Science & Engineering
August 1, 2022 – June 1, 2026
YouTube Video RAG Assistant
June 29, 2026 – Present
Built a multi-video RAG research assistant that ingests transcripts from multiple YouTube URLs simultaneously and answers cross-video questions, removing the need to manually watch source videos. Designed a retrieval pipeline using HuggingFace embeddings (all-MiniLM-L6-v2) indexed in FAISS for semantic search, paired with Llama 3.1 (8B) served via the Groq API for low-latency response generation. Implemented automatic topic extraction and one-click summary generation (concise, detailed, and study-notes modes) through an interactive Streamlit chat interface.
View ProjectCiteMind - Multi-Document RAG Assistant
June 29, 2026 – Present
Developed a multi-document RAG application supporting PDF, DOCX, and PPTX ingestion, enabling users to query across heterogeneous document sets and receive citation-backed answers. Engineered a Hybrid Search pipeline combining semantic vector search (ChromaDB + HuggingFace embeddings) with keyword-based BM25 search, fused via Reciprocal Rank Fusion (RRF) for higher retrieval accuracy. Used Llama 3.1 via Groq to generate answers with precise in-line source-filename citations, and exposed the underlying retrieved text chunks in the UI for full source transparency.
View ProjectReviewLens – Fake Review Detection System
June 29, 2026 – Present
Built a hybrid deception-detection system for hotel reviews combining TF-IDF semantic features with handcrafted stylometric features (vocabulary diversity, punctuation intensity, personal-pronoun ratio) to capture both content and writing style. Trained a Random Forest classifier on the combined feature set, achieving 89.7% accuracy in distinguishing genuine from deceptive reviews. Deployed the model behind a Flask web application for real-time, interactive review analysis end-to-end.
View ProjectPython for Data Science
NPTEL
January 1, 2024 – Present
Fundamental Algorithms: Design and Analysis
NPTEL
January 1, 2024 – Present
The Joy of Computing using Python
NPTEL
January 1, 2023 – Present
Problem Solving Through Programming in C
NPTEL
January 1, 2023 – Present
Cultural Fit Analysis
The candidate's academic projects show a strong interest in cutting-edge AI/ML applications, particularly in RAG and NLP, which aligns well with an AI Engineer role. The diversity of projects (video RAG, multi-document RAG, fake review detection) indicates a broad curiosity and ability to apply AI concepts to different problem domains. The certifications in Python and Algorithms further support a continuous learning mindset. However, the lack of professional experience means cultural fit in a collaborative, fast-paced industry setting is unproven.
Soft Skills & Operational Fit
The candidate demonstrates a proactive and hands-on approach to learning and project development, indicating strong self-motivation and problem-solving skills. The emphasis on 'implementing core logic from scratch' suggests a detail-oriented and deep technical understanding. However, without professional experience, operational fit in a team or corporate environment is yet to be fully assessed.