Hanif Lashari
(he/him)
AI and Machine Learning Engineer • Data Scientist • Researcher in Real-Time Intelligent Systems
Professional Summary
AI and Machine Learning Engineer with 3+ years of experience building intelligent systems across healthcare, cybersecurity, and IoT domains. Skilled in developing production-ready models, scalable data pipelines, and automation workflows that bridge AI research and real-world deployment.
At Iowa State University, Hanif designed predictive models for robotic surgery using Informer transformers and optimized QUIC congestion control (BBRv2-TI) for ultra-low-latency communication. At Mary Greeley Medical Center, he engineered real-time anomaly detection using Zeek and OpenSearch ML, built retrieval-augmented assistants with Ollama and LangChain, and deployed on-premise data analytics pipelines.
Hanif’s expertise spans deep learning, reinforcement learning, anomaly detection, and RAG systems, with a strong foundation in Python, PyTorch, and modern MLOps practices. His mission is to create adaptive, data-driven systems that make real-time decisions with reliability and transparency.
Education
PhD in Computer Engineering (AI/ML)
Iowa State University
MEng in Electrical Engineering
Mehran University of Engineering and Technology
BE in Electronics Engineering
Mehran University of Engineering and Technology
Interests
My research lies at the intersection of Artificial Intelligence, Data Science, and Next-Generation Internet technologies to enable real-time intelligent systems for healthcare and robotics.
I focus on building AI-driven predictive and control frameworks that ensure precision, reliability, and ultra-low latency in Tactile Internet applications such as remote robotic surgery.
This includes:
-
Developing Informer-based transformer models for real-time position prediction under delay, jitter, and packet loss.
-
Designing Kalman Filter and MOESP-based estimation frameworks for accurate state estimation of surgical robots.
-
Optimizing congestion control algorithms (BBRv2-TI) for QUIC networks to achieve utility-guided performance across throughput, delay, and loss.
-
Leveraging IoT and edge intelligence for sustainable environment management and energy-efficient communication systems.
My broader goal is to bridge AI and network optimizationenabling intelligent, resilient, and data-driven systems that perform reliably in mission-critical, delay-sensitive environments.
I am always open to collaborations in AI for healthcare, real-time systems, and intelligent network design.