Help & Supportcareers@gravityer.com
AI Engineer with less than a year in NLP & RAG 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
Software Engineer with a focus on AI/ML and NLP, having built end-to-end projects including Agentic RAG systems, intelligent document assistants, and financial sentiment analysis pipelines. Proficient in Python, LangChain, LangGraph, FastAPI, and vector databases, with practical experience integrating LLMs into production-ready applications.
FAST-NUCES
BS Software Engineering · Software Engineering
N/A – June 30, 2025
CODIRO Technologies
MERN Stack Developer Intern
January 1, 2026 – February 1, 2026
Pakistan
Agentic Research Assistant with LangGraph RAG Pipeline
January 1, 2026 – Present
Built an Agentic RAG research assistant using LangGraph and LangChain with a multi-step workflow for retrieval, evaluation, and response generation. Designed a complete pipeline including document ingestion, text chunking, embedding generation, vector search, query routing, and LLM-based answer generation. Implemented intelligent routing and fallback workflows that evaluate retrieved context and trigger web search when relevant information is unavailable in the knowledge base. Integrated state management and modular AI nodes to support semantic search, query handling, and structured research responses.
AI-Powered RAG Document Assistant
January 1, 2026 – Present
Built a full-stack intelligent document assistant using Python (FastAPI) and LangChain that allows users to upload PDF, DOCX, CSV, and TXT files and receive AI-generated answers with citations. Implemented a complete Retrieval-Augmented Generation (RAG) pipeline with semantic search using Qdrant vector database and HuggingFace embeddings. Integrated Groq LLM with real-time streaming responses for fast and context-aware question answering. Designed scalable document ingestion, chunking, embedding generation, and retrieval workflows for efficient knowledge extraction.
Stock Sentiment Analysis using NLP & Machine Learning
January 1, 2025 – Present
Built an end-to-end NLP pipeline to analyze financial news headlines and predict stock market movement using TF-IDF, Logistic Regression, BERT embeddings. Performed text preprocessing, feature engineering, sentiment analysis, and comparative model evaluation on real-world financial datasets. Implemented machine learning workflows for training, validation, and performance optimization of NLP models. Visualized insights and model performance metrics to compare traditional ML techniques with transformer-based embeddings.
Cultural Fit Analysis
The candidate's project portfolio is highly aligned with an AI Engineer role, showcasing a strong interest and practical application in the field. The diversity of projects (Agentic RAG, Document Assistant, Sentiment Analysis) demonstrates a breadth of application within AI/ML. However, the candidate's only professional experience is a MERN Stack Developer internship, which, while demonstrating software development skills, is not directly in AI/ML. This suggests a strong passion for AI but limited professional experience in the domain, which might require mentorship and integration into an AI-focused team culture.
Soft Skills & Operational Fit
The candidate's project descriptions indicate a proactive and self-directed approach to learning and application of advanced AI concepts. The detailed project descriptions suggest good problem-solving skills and an ability to articulate technical solutions. However, without specific psychometric or English test results, a comprehensive assessment of soft skills, work attitude, stress handling, and team collaboration is not possible.