Dharanitheja Kanjeri

About Dharanitheja Kanjeri

Generative AI Engineer with 5+ years of experience building production-grade AI systems across machine learning, data science, and enterprise Generative AI applications. I specialize in Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), and enterprise AI copilots that enable intelligent knowledge discovery at scale. Currently, I design and deploy real-time GenAI solutions using LangChain, vector databases, and cloud-native infrastructure. My work focuses on building scalable RAG pipelines, optimizing prompt performance, and implementing LLMOps frameworks with monitoring, safety guardrails, and access-aware retrieval for secure enterprise deployments. Previously, I developed end-to-end machine learning platforms, including customer churn prediction systems that improved retention and protected $1.8M+ in annual revenue. I bring strong expertise in Python, AWS, Kubernetes, and distributed data systems, with a focus on translating complex business problems into production-ready AI solutions. I’m passionate about building reliable, scalable, and secure AI systems that deliver measurable business impact. Core Expertise: • Generative AI & LLM Applications • Retrieval-Augmented Generation (RAG) • Enterprise AI Copilots • LLMOps / MLOps • Cloud-Native AI Deployment (AWS, Kubernetes)

Experience

1. Generative Ai Engineer

   Glean

   May 2025 — Present · US

   Built a production-grade enterprise AI copilot for unified workplace search using RAG architecture, serving 5K+ daily users and improving knowledge discovery efficiency. Architected an enterprise knowledge platform integrating fragmented tools using Python, LangChain, and LlamaIndex, processing 12M+ documents. Engineered high-performance RAG pipelines using Pinecone and FAISS with OpenAI GPT and LLaMA, enabling permission-aware semantic search. Optimized LLM performance using prompt engineering, context enrichment, and query rewriting, reducing hallucinations and improving response accuracy. Deployed real-time AI search services using FastAPI, Docker, and Kubernetes on AWS, achieving sub-120ms latency. Implemented enterprise LLMOps pipelines using LangSmith, MLflow, and Weights & Biases with Guardrails AI for compliance and security

Education

• Youngstown State University

  Master of Science, Data Science and Statistics