Hi, I'm
Umair Inayat
Agentic AI Engineer
Agentic AI Engineer @ Spark AI working across the full stack: autonomous multi-agent systems and LLM automation, backend APIs and RAG pipelines, plus deep learning and computer vision from training to production.
About Me
Agentic AI, Backend & Vision in Production
I'm an Agentic AI Engineer at Spark AI, where I build autonomous multi-agent systems and LLM-powered automation for real businesses: lead-qualification agents with CRM integration, n8n and LangGraph orchestration, RAG pipelines, and computer vision for document- and image-based tasks. Previously I was an AI Full Stack Engineer at A'sTechware, shipping RAG pipelines, agent orchestration, and production AI features across Node.js and FastAPI with React on the front.
I graduated from the University of Management and Technology with a BS in Computer Science and a 3.82 CGPA, earning four merit awards including the Dean's and Rector's Awards. My final year project, Radisist, an AI radiology diagnostics platform, placed in the top 10 out of 160 projects. I also spent nearly two years as a Teaching Assistant for Deep Learning and Theory of Automata.
Outside work I ship open source and publish models on Hugging Face, tools like DeepContext (hierarchical memory for AI agents) and medical-imaging work like Radisist, alongside computer vision and applied ML research. I led the AI/ML team at Google Developer Group on Campus UMT and served as a Beta Microsoft Student Ambassador, organizing tech summits across 15 universities.
Journey
Experience & Education
My professional journey, academic background, and leadership roles
Sep 2026 - Present
Agentic AI Engineer
Designing and building autonomous AI agents and LLM-powered automation for real-world businesses at Spark AI, a Dubai-based AI automation and consulting agency. Architecting multi-step agent orchestration with n8n, LangGraph, and Claude/OpenAI APIs, CRM-integrated lead qualification agents, RAG pipelines, computer vision extensions for document/image tasks, and Slack/CRM human-in-the-loop escalation flows. Owning the agent lifecycle end-to-end: prototyping, testing, deployment, and monitoring.
Jan 2026 - Aug 2026
AI Full Stack Engineer
A'sTechware
Built AI-powered applications, backend systems, and automation platforms for production use. Designed backends and APIs in Node.js and Ruby on Rails with React on the frontend, and integrated LLMs and GenAI into real business workflows: prompt engineering, RAG pipelines, agentic workflows, and vector databases.
Oct 2025 - Jul 2026
Teaching Assistant
University of Management and Technology
TA for Deep Learning and Theory of Automata. Assisted with labs in Python, PyTorch, and TensorFlow, conducted graded assessments, and gave one-on-one guidance on neural networks and automata design.
Jul 2025 - Sep 2025
AI/ML Intern
Texense
Selected for the Texense Summer Internship Program 2025. Contributed to production-level AI/ML solutions under industry mentorship, focusing on model development, optimization, and deployment.
Mar 2024 - Oct 2025
Teaching Assistant
University of Management and Technology
Assisted in teaching OOP, Data Structures, Database Systems, ML/DL, and Operating Systems. Mentored students in complex programming concepts.
Nov 2023 - Feb 2024
Peer Mentor
University of Management and Technology
Peer tutor for Programming Fundamentals in Fall 2023.
Tech Stack
Technical Skills
Backend, GenAI, and ML technologies I work with daily
AI & GenAI
Backend & APIs
ML & Computer Vision
Frontend & Infra
Portfolio
Main Projects
The work I would want to be judged on. Each one has its own write-up.
Radisist: Medical Imaging AI Platform
Final year project. Trained a BiomedCLIP modality router on 14k images reaching 100% test accuracy, plus SMP UNet++ segmentation models hitting 95% accuracy and 88.5% Dice across 7 imaging modalities. Models published to Hugging Face behind a full-stack Django platform with REST endpoints and PostgreSQL-backed patient data pipelines.
Sehat Guftagu
LLM-powered bilingual (Urdu/English) clinical web app using LangGraph multi-agent orchestration across 5 modular AI services for patient triage, symptom analysis, and report generation. Structured output parsing and entity extraction with PostgreSQL storage behind a clean FastAPI backend.
Document Intelligence
Scalable RAG pipeline with multi-source document ingestion (PDF, DOCX, HTML, images) and semantic search over vector embeddings, combining dense and sparse hybrid retrieval. Tuned with chunking strategies, re-ranking, and query augmentation, containerized for reproducible ML-ready deployment.
Plus 24 more repositories across backend, ML, research, and coursework.
Recognition
Achievements & Certifications
Competition placements, academic awards, and professional certifications
Competitions & Rankings
Radisist, Final Year Project
Ranked in the top 10 of 160 FYP projects at UMT for AI radiology diagnostics
2026
TechnoVerse Comsat ML Competition
66 tree species classification with 118k instances
2025
SofTech 2025 ML Challenge
Hospital readmission prediction at FAST Lahore, national-level, 30 teams
2025
Awards
Dean's Award
Fall 2023
Rector's Award
Fall 2024, 4.0 GPA
Dean's Award
2025
Merit Award
Spring 2025
Certifications
LLMs & MCPs
Hugging Face
Machine Learning Specialization
Andrew Ng / Coursera
Deep Learning Specialization
Coursera
Data Scientist in Python
DataCamp
Microsoft Certified: Azure Data Fundamentals
Microsoft
MLOps Bootcamp
10+ End-to-End ML Projects
Get in Touch
Let's Build Something Together
Open to backend, AI, and GenAI engineering work, research collaborations, and open-source projects. Feel free to reach out!