AI Engineer with 1+ years in LLM Systems and Production Deployment
AI is analyzing your overall score…
Identifying your key strengths…
Evaluating your skill match against the job requirements…
Assessing your cultural and operational fit
Production-focused Generative AI Engineer who architects, deploys, and operates LLM-powered systems at commercial scale. Engineered a Python/Flask LLM email automation API (Groq) handling 50+ daily B2B requests with 80% reduction in manual workload; a full-duplex WebSocket voice agent achieving sub-200ms end-to-end latency; and a multilingual conversational AI backend processing English and Urdu via WhatsApp. Building AURA OS - a multi-agent autonomous AI system shortlisted for the Google AI Seekho Hackathon. Deploys exclusively to production on AWS and Docker. Thinks in LLM pipelines, ships in production.
University of Lahore
BS Embedded Systems
August 1, 2024 – June 30, 2028
Punjab Group of Colleges
Intermediate · Pre-Medical
June 1, 2022 – May 31, 2024
Afrium
Founding Campus Ambassador
June 1, 2026 – Present
Pakistan
DecodeLabs
Artificial Intelligence Intern
April 1, 2026 – May 1, 2026
India
Fiverr (manaal_ai)
AI Automation Engineer
April 1, 2026 – Present
Pakistan
Pakistan Health Parliament
Head of Digital Media
February 1, 2026 – Present
Lahore, Punjab, Pakistan
Lojics
Business Development Executive
January 1, 2026 – March 1, 2026
Unknown
DS Trainings
WordPress Developer
July 1, 2025 – December 1, 2025
Lahore, Punjab, Pakistan
Brain Creatives
Digital Presence Manager
March 1, 2025 – June 1, 2025
Lahore, Punjab, Pakistan
enARtifi
Associate Digital Presence Manager
February 1, 2025 – June 1, 2025
Lahore, Punjab, Pakistan
ZUNF Medicare / PITB Incubation Wing / HiSkyTech
Graphics Designer & Digital Marketer
July 1, 2024 – December 1, 2024
Lahore, Punjab, Pakistan
AURA OS - Multi-Agent Generative AI System
June 1, 2026 – Present
Autonomous multi-agent AI operating system that transforms unstructured inputs into coordinated LLM-driven actions under real-world constraints. Shortlisted for the Google AI Seekho Hackathon as the flagship advanced agentic AI project. Architected a multi-agent orchestration layer with event-driven coordination → specialized LLM agents own discrete operational domains and communicate via a shared event bus, eliminating single-agent bottlenecks. Engineered structured-output LLM reasoning pipelines with grounded, auditable decision boundaries using Groq; prevents hallucinated actions in mission-critical agentic workflows. Built real-time operational state machines that detect anomalies and autonomously re-prioritize tasks without human intervention – deployed with full observability and recovery logging. Implemented graceful degradation architecture: agents fail independently without cascading failures; autonomous recovery is logged and observable on AWS-hosted infrastructure.
LLM Email Automation API
June 1, 2026 – Present
Automated triage and response system for 50+ daily inbound B2B emails eliminating manual classification and scaling team throughput without headcount increases. Built a Python Flask REST API routing inbound requests through Groq LLM: intent classification → context-aware response generation → Gmail API dispatch → Google Sheets CRM persistence – full AI workflow automation. Dockerized and deployed on Railway with a Streamlit operator dashboard; commercially distributed via Gumroad with Zapier/Make webhook templates for no-code client onboarding. Delivered 80% reduction in manual email handling; system operates autonomously with zero ongoing engineering intervention – demonstrating production-grade AI deployment at scale.
Multilingual WhatsApp Conversational AI Backend
June 1, 2026 – Present
Engineered a webhook handler pipeline: Deepgram STT voice transcription → Groq LLM response generation → structured data persistence, supporting 24/7 multilingual consumer handling in English and Urdu. Designed discrete microservice layers enabling independent component swapping without full redeployment – reduced response latency from hours to seconds with full language and LLM model extensibility.
Edge AI Surveillance Platform
June 1, 2026 – Present
AI-powered ESP32-CAM surveillance with motion detection, face recognition, and Firebase Realtime Database integration; paired with Google Voice + MIT App Inventor mobile app for live alerts and remote monitoring; model-swappable without reflashing.
Real-Time AI Voice Agent (Priya)
June 1, 2026 – Present
Low-latency conversational AI calling system engineered for full-duplex real-time voice dialogue - eliminating HTTP polling overhead. Architected a full-duplex WebSocket pipeline: audio in → Deepgram STT → Groq LLM inference → TTS synthesis → audio out, achieving sub-200ms end-to-end latency in live production operation. Engineered persistent session state management across conversation turns; structured entity extraction writes to CRM automatically via REST API - fully integrated conversational AI workflow. Deployed with interruption handling, dynamic follow-up generation, and a self-serve analytics dashboard – production-grade AI deployment on cloud infrastructure.
LensIQ AI Production Computer Vision Pipeline
June 1, 2026 – Present
Engineered a multi-pipeline AI vision system: YOLO object detection with confidence scoring → OCR text extraction → LLM-powered automated scene summarization → annotated visualization – full detection-to-insight pipeline. Deployed an interactive visual question-answering module enabling natural-language image queries, allowing non-technical users to interact with CV inference directly via Streamlit.
ESP32 IoT Occupancy System
June 1, 2026 – Present
Ultrasonic sensor fusion with interrupt-driven firmware; live telemetry streamed to ThingSpeak cloud dashboard; schema designed for zone expansion without firmware changes.
Programming Fundamentals
Duke University & UC Santa Cruz
June 1, 2026 – Present
AWS Student Community Day - National Delegate
Enterprise Cloud Forum
June 1, 2026 – Present
Raspberry Pi & Python Programming
University of California, Irvine
June 1, 2026 – Present
Certiport Cloud Specialist
Microsoft / Cloud Fundamentals
June 1, 2026 – Present
AI Connect 2026
University of Lahore
June 1, 2026 – Present
Cultural Fit Analysis
The candidate exhibits a strong drive for innovation and practical application of AI, aligning well with a dynamic, product-focused AI engineering culture. Their involvement in the Google AI Seekho Hackathon and various community/ambassador roles suggests a collaborative spirit and a desire to contribute to the broader AI ecosystem. The diverse range of projects, including personal initiatives and freelance work, indicates self-motivation and a continuous learning mindset. The focus on delivering commercialized solutions and achieving measurable business outcomes (e.g., 80% reduction in manual email handling) demonstrates a business-oriented approach, which is crucial for aligning technical work with organizational goals. The candidate's early career stage combined with significant practical experience suggests a high potential for growth and a willingness to take on new challenges.
Soft Skills & Operational Fit
The candidate demonstrates strong initiative and a proactive approach to learning and applying AI technologies, as evidenced by their freelance work and participation in hackathons and community roles. Their project descriptions highlight a focus on production-grade deployment, real-world constraints, and measurable impact, indicating a practical and results-oriented mindset. The emphasis on observability, recovery, and graceful degradation points to a mature understanding of operational excellence. The candidate's ability to work on diverse projects, from multi-agent systems to conversational AI and computer vision, suggests adaptability and a broad technical curiosity. The experience in community building and digital media also indicates good communication and collaboration potential, which are valuable for cross-functional teams.