Building production AI systems

I’m an AI/ML Engineer with 7+ years of experience working across Machine Learning, Deep Learning, NLP, Statistical Modeling, and Generative AI. My focus has evolved from traditional data science and predictive modeling toward building production-grade AI systems that can retrieve information, reason over data, use tools, and execute complex workflows.

My recent work has focused heavily on Generative AI, Agentic AI, and Retrieval-Augmented Generation (RAG). I have designed and developed LLM-powered applications involving document ingestion, intelligent retrieval, vector search, reranking, structured data access, agent orchestration, and grounded response generation. I enjoy working at the intersection of AI research, software engineering, and real-world business problems.

My engineering toolkit includes Python, LangChain, LangGraph, Azure OpenAI, Databricks, vector databases, Docker, Redis, Qdrant, Neo4j, and modern cloud-based AI architectures. I have worked with both structured and unstructured data and have experience designing pipelines that take AI applications from experimentation toward reliable production systems.

I’m particularly interested in the engineering challenges behind trustworthy AI—evaluation, hallucination reduction, grounding, guardrails, observability, regression testing, and building systems that can be measured rather than simply demonstrated.

Beyond GenAI, my background includes classical machine learning, time-series analysis, anomaly detection, NLP, computer vision, and deep learning. This gives me a broader perspective on choosing the right approach for a problem rather than treating an LLM as the solution to everything.

I’m currently focused on becoming an even stronger AI systems engineer—building AI agents and intelligent applications that are reliable, observable, scalable, and genuinely useful in production.