AI Engineer with 1+ years in Generative AI, RAG pipelines & MLOps.
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 1 year of hands-on experience building production-grade Generative AI systems, Agentic AI workflows, and RAG pipelines. Specialized in multi-agent architectures, retrieval optimization, and scalable LLM applications using LangGraph, FastAPI, and vector databases. Experienced in deploying AI systems with Docker, Redis, CI/CD, and async backend architectures for real-world production environments.
City University of Science & Information Technology
BS · Software Engineering
August 1, 2022 – June 30, 2026
AfryvoAnalytics
AI Engineer
March 1, 2026 – April 1, 2026
India
Codecelix, NASTP Rawalpindi
AI Engineer Intern
November 1, 2025 – February 1, 2026
Rawalpindi, Punjab, Pakistan
BlackByt3, Islamabad
AI/ML Engineer Intern
May 1, 2025 – October 1, 2025
Islamabad, Islamabad Capital Territory, Pakistan
AI Copilot with Persistent Memory & Tooling
June 23, 2026 – Present
Built AI assistant with vector-based episodic memory and summary compression for multi-turn retention, improving relevance by ~30%. Reduced retrieval latency by 35% (3.2s -> 2.1s P50) via async chunking, query rewriting, and 5+ external tool integrations.
View ProjectAutonomous AI Data Analyst Agent
June 23, 2026 – Present
Engineered production multi-agent system (LangGraph + ReAct) for autonomous CSV/SQL analysis deployed on HuggingFace Spaces, serving 100+ active users. Built sandboxed Chat with Data interface with PII masking and async processing, reducing manual analysis effort by 60% vs. human baseline. Achieved <2s end-to-end latency via DataFrame caching, async pipeline orchestration, and parallel agent node execution.
View ProjectGraph-Based Agentic Knowledge Graph-RAG System
June 23, 2026 – Present
Architected Knowledge Graph-RAG system (FAISS + Neo4j + cross-encoder reranking) over 50K+ docs; <500ms P95 retrieval latency. Implemented Planner-Executor-Validator loop; RAGAS faithfulness improved 0.61->0.84, cutting hallucination by 35%. Redis semantic caching reduced LLM API costs by 40%; secured with JWT, RBAC, rate limiting, and full audit logging.
View ProjectFraud Detection System
June 23, 2026 – Present
Built end-to-end fraud detection pipeline (XGBoost, Random Forest, Isolation Forest) on imbalanced data; achieved F1 0.85, ROC-AUC 0.97, and <100ms inference latency. Applied SMOTE and class-weighted optimization; model selection guided by Precision-Recall and ROC-AUC analysis.
View ProjectAgentic AI with LangChain & LangGraph
IBM
June 1, 2026 – Present
Retrieval Augmented Generation
Coursera
June 1, 2026 – Present
Generative AI for Everyone
DeepLearning.AI
June 1, 2026 – Present
Cultural Fit Analysis
The candidate shows a strong passion for AI/ML through diverse personal projects and certifications, aligning well with an AI Engineer role. The breadth of technologies used (LangGraph, FAISS, Neo4j, FastAPI, Docker) and the focus on end-to-end system development indicate a proactive and versatile individual. However, the limited professional experience (1 year, including internships) and the focus on personal projects might suggest a need for more exposure to large-scale team environments and corporate processes, which could impact cultural integration in a fast-paced, established team.
Soft Skills & Operational Fit
The candidate's project descriptions highlight problem-solving, optimization, and a results-oriented approach (e.g., 'cutting manual processing effort by ~40%', 'improving relevance by ~30%'). The experience in deploying systems and managing CI/CD suggests an operational mindset. However, without direct interview data, soft skills like teamwork and communication in a collaborative setting cannot be fully assessed.