I am an AI/ML Engineer with over 2+ years of experience building production agentic AI systems and multi-agent orchestration. I specialize in designing and deploying autonomous workflows using advanced frameworks such as LangChain, LangGraph, and MCP to enable complex reasoning, tool-calling, durable execution, and task orchestration. My expertise includes architecting multi-LLM proxy systems capable of intelligent routing and handling over 10,000 daily API calls.
Currently, I am developing a knowledge graph-enhanced database agent to facilitate natural language data retrieval. I have a strong foundation in cloud-native deployment, particularly with AWS services, and I am experienced in Retrieval-Augmented Generation (RAG) architectures and production ML systems. I have published more than 60 technical articles on AI system design and implementation, demonstrating my commitment to knowledge sharing and thought leadership.
In my current role, I design and deploy generative AI applications, including RAG-based conversational agents for chat, voice, and simulation workflows. I have built enterprise-grade conversational chatbots integrating custom SQL agents and agentic workflows for database access. I also architect scalable evaluation pipelines and multi-LLM proxy servers that optimize API orchestration and reduce rate limit errors significantly.
I have developed end-to-end ETL pipelines to automate data integration for AI workflows and implemented multi-modal video analysis pipelines to enrich RAG responses. Additionally, I have deployed AI-powered outreach automation systems that leverage feature engineering from CRM data to enable personalized customer messaging at scale.
My projects include building multi-agent research systems coordinating specialized agents with memory and context-aware collaboration, developing database agents with knowledge graphs, and creating production recommendation engines using vector databases. I have hands-on experience with containerized AI applications on AWS ECS, automated CI/CD pipelines, and advanced transformer architectures including Vision Transformers, Llama-2, and GPT-2.
I am passionate about pushing the boundaries of AI and machine learning by combining deep technical expertise with practical deployment skills to deliver scalable, reliable, and innovative AI solutions.
Specialization in AI, Machine Learning, NLP Deep Learning. Final-year project applied Deep Reinforcement Learning to solve an electrical engineering domain problem, culminating in a published research paper.
Designed and deployed production Generative AI applications including RAG-based conversational agents for chat, voice, and simulation workflows using OpenAI, Gemini, and Anthropic models, serving 10,000+ daily interactions. Built enterprise conversational chatbot with custom SQL agents integrating structured data management with agentic workflows. Architected scalable evaluation pipeline with AWS Lambda and SQS processing 1,000+ transcripts in under 1 minute, implementing monitoring and logging. Engineered enterprise-grade multi-LLM proxy server managing real-time API orchestration with intelligent key pooling and monitoring, reducing rate limit errors by 40%. Developed end-to-end ETL pipeline using Mage framework for automated data integration. Implemented multi-modal video analysis pipeline enriching RAG pipeline with video-derived context. Deployed AI-powered outreach automation system using feature engineering from CRM data. Architected and deployed containerized AI applications on AWS ECS with Application Load Balancer, VPC configuration, and automated CI/CD pipelines achieving zero-downtime.
Jobicy
588 professionals pay to access exclusive and experimental features on Jobicy
Free
USD $0/month
For people just getting started
Plus
USD $8/month
Everything in Free, and: