Looking for a job

Rehan Khan

@rehankhan

Message

AI/ML engineer specializing in Retrieval-Augmented Generation and multi-agent systems.

India

Message

What I'm looking for

I seek roles building production-grade AI systems (RAG, agents, MLOps) in collaborative, ethics-focused teams where I can lead delivery, mentor engineers, and scale robust ML infrastructure.

I am an AI/ML engineer with hands-on experience building scalable RAG systems, multi-agent orchestration, and cloud-agnostic ingestion pipelines that improve retrieval precision and reduce latency.

I designed a modular, multi-agent RAG infrastructure and a Model Context Protocol layer to streamline tool calling and integrations, and I delivered containerized FastAPI backends for consistent deployments across Azure and AWS.

My work has reduced retrieval latency by 40%, improved precision by 30%, cut deployment setup times by 70%, and implemented safeguards that lowered unsafe queries by 95%. I have also led and mentored small engineering teams and coordinated development sprints.

I publish and maintain projects (including a PyPI package), fine-tune LLMs, build data extraction pipelines, and pursue applied research in conversational AI and semantic analysis. I seek to join teams focused on production-grade AI systems and robust, ethical ML deployments.

Experience

Work history, roles, and key accomplishments

Current

AI/ML Engineer

Current

Dailoqa

Apr 2025 - Present (8 months)

Designed a modular multi-agent RAG infrastructure and Model Context Protocol, reducing retrieval latency by 40% and integration overhead by 35%; engineered cloud-agnostic ingestion for 10K+ documents and delivered containerized FastAPI deployments reducing configuration overhead by 70%.

Python fastAPI Docker Vector Databases Cloud NLP System Design

AI Engineer

Stealth Startup

Jan 2024 - Apr 2025 (1 year 3 months)

Built Helpdesk Assessment and RAG systems that categorized 5M+ tickets, reduced info retrieval time from 10–15 mins to <1 min, and improved query resolution efficiency by ~30%; designed Multi-AI Agent workflows and optimized document extraction pipelines, cutting manual review time by 60%.

Python RAG LangGraph InfluxDB NLP System Integration

Summer Intern

National Institute of Technology Trichy

May 2023 - Jul 2023 (2 months)

Conducted network lateral movement research and applied ML-based cyber deception and anomaly detection, reducing false positives by 15% and improving incident response efficiency.

Cybersecurity Anomaly Detection Machine Learning Research Python Experimentation