AI Engineer with less than a year in LLM Applications & 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
AI Engineer with experience building LLM powered applications, Agentic AI systems, RAG pipelines, and backend services. Skilled in Python, FastAPI, LangChain, OpenAI, Claude, Ollama, vector databases, prompt engineering, and production ready AI applications.
FAST National University of Computer and Emerging Sciences
B.S. · Artificial Intelligence
August 1, 2022 – June 30, 2026
Tufail Shaheed Army College
F.Sc. · Pre-Engineering
June 1, 2019 – May 31, 2021
Markhor Systems
AI Engineer
February 1, 2026 – Present
Islamabad, Islamabad Capital Territory, Pakistan
RoohAI - Emotional Digital Twin
June 1, 2026 – June 1, 2026
Worked on an AI powered system involving intent detection, sentiment analysis, and LLM-based response generation. Integrated speech and language capabilities including STT, TTS, and ElevenLabs API for improved user interaction. Applied prompt engineering and API orchestration to support natural, context aware conversations.
Agentic RAG Chatbot System
June 1, 2026 – June 1, 2026
Built an Agentic RAG chatbot capable of retrieving information from custom knowledge bases and generating context aware answers. Implemented document ingestion, chunking, embedding generation, semantic retrieval, prompt engineering and LLM response generation. Integrated tool using workflows where the LLM could interact with external APIs and structured backend logic. Used FAISS for local vector search and optimized retrieval quality through chunking and prompt refinement.
View ProjectAI Document Parsing and Automation Pipeline
June 1, 2026 – June 1, 2026
Developed an AI document processing pipeline to extract, chunk, summarize, and organize documents automatically. Built backend APIs using FastAPI and integrated Ollama based LLM inference for document understanding and summarization. Used Supabase for data storage and workflow management, enabling searchable and reusable document intelligence. Applied pipeline automation and deployment practices to improve repeatability and maintainability.
FabrIQ - Fabric Defect Detection System
June 1, 2026 – June 1, 2026
Built a real time computer vision system using YOLO to detect and classify fabric defects for textile quality inspection. Handled model training, dataset preparation, evaluation, and system testing. Designed the solution to support automated inspection and reduce manual quality checking effort in textile production.
Google Prompting Essentials Specialization
June 1, 2026 – Present
Introduction to Generative AI
Google Cloud
June 1, 2026 – Present
Google IT Automation with Python
June 1, 2026 – Present
Programming for Everybody
University of Michigan
June 1, 2026 – Present
Machine Learning Specialization
DeepLearning.AI and Stanford University
June 1, 2026 – Present
Cultural Fit Analysis
The candidate's project portfolio showcases a strong interest and practical experience across various domains within AI, including LLM-powered chatbots, document automation, emotional digital twins, and computer vision for defect detection. This diversity, coupled with experience in an AI Engineer role at Markhor Systems, aligns well with a dynamic, innovation-focused environment. The certifications further demonstrate a proactive learning attitude. The candidate's experience level is listed as 0, but the projects and current role suggest more practical exposure than a typical entry-level candidate, indicating a strong drive and initiative that would fit well into a growth-oriented culture.
Soft Skills & Operational Fit
The candidate's resume indicates a strong focus on practical project implementation and deployment, suggesting a results-oriented approach. The diversity of projects implies adaptability and a willingness to tackle different AI challenges. However, without specific psychometric or English test results, it's difficult to assess communication clarity, work attitude, stress handling, or team collaboration directly. The project descriptions are clear and concise, which is a positive indicator for written communication.