I am a Generative AI Engineer with 5 years of experience spanning data science and production-grade AI systems. I specialize in LLMs, retrieval-augmented generation (RAG) architectures, and enterprise AI copilots, building scalable, real-time solutions using LangChain, vector databases, and cloud-native deployment. I translate complex business problems into end-to-end AI solutions, design robust ML pipelines, and implement prompt optimization and safety guardrails. My work has driven measurable impact, including churn prediction systems that boosted retention and protected $1.8M in annual revenue. I’m proficient in Python, AWS, Kubernetes, and distributed data systems, with a focus on enterprise knowledge retrieval and AI copilots.

Dharani Theja Kanjeri

I am a Generative AI Engineer with 5 years of experience spanning data science and production-grade AI systems. I specialize in LLMs, retrieval-augmented generation (RAG) architectures, and enterprise AI copilots, building scalable, real-time solutions using LangChain, vector databases, and cloud-native deployment. I translate complex business problems into end-to-end AI solutions, design robust ML pipelines, and implement prompt optimization and safety guardrails. My work has driven measurable impact, including churn prediction systems that boosted retention and protected $1.8M in annual revenue. I’m proficient in Python, AWS, Kubernetes, and distributed data systems, with a focus on enterprise knowledge retrieval and AI copilots.

Available to hire

I am a Generative AI Engineer with 5 years of experience spanning data science and production-grade AI systems. I specialize in LLMs, retrieval-augmented generation (RAG) architectures, and enterprise AI copilots, building scalable, real-time solutions using LangChain, vector databases, and cloud-native deployment.

I translate complex business problems into end-to-end AI solutions, design robust ML pipelines, and implement prompt optimization and safety guardrails. My work has driven measurable impact, including churn prediction systems that boosted retention and protected $1.8M in annual revenue. I’m proficient in Python, AWS, Kubernetes, and distributed data systems, with a focus on enterprise knowledge retrieval and AI copilots.

See more

Experience Level

Expert
Expert
Expert
Expert
Expert
Expert
Expert
Expert
Expert
Expert
Expert
Expert
Intermediate
See more

Work Experience

Generative AI Engineer at Glean
May 1, 2025 - Present
Build a production-grade enterprise AI copilot for unified workplace search using RAG architecture, integrating LLMs, real-time deployment, LLMOps, and access-aware retrieval, serving 5K+ users daily. Architect enterprise knowledge platform by integrating fragmented tools with Python, LangChain, and LlamaIndex, processing 12M+ documents and significantly reducing cross-platform information retrieval time. Engineer high-performance RAG pipelines using Pinecone and FAISS with OpenAI GPT and LLaMA, enabling permission-aware semantic search and improved contextual responses for concurrent enterprise queries. Optimize LLM performance with prompt engineering across OpenAI GPT and Claude, reducing hallucinations and improving answer relevance for enterprise knowledge workflows. Lead deployment of real-time enterprise AI search services using FastAPI, Docker, and Kubernetes on AWS Bedrock and EC2, achieving sub-120ms latency and reducing infrastructure costs through optimized retrieval and cac
Data Scientist at Tata Consultancy Services
June 1, 2020 - August 1, 2024
Built a production-grade, end-to-end churn prediction platform evolving from basic analytics to real-time, scalable ML systems with MLOps and cloud deployment, driving enterprise-wide data-driven retention strategies. Architected customer churn prediction solution by translating ambiguous business requirements into machine learning objectives, engineered features using Python, Pandas, NumPy, improving ROC-AUC from 0.72 to 0.89. Engineered scalable data pipelines integrating multi-source datasets from PostgreSQL, MySQL, and AWS S3, leveraging SQL and PySpark, processing 10M+ records daily while reducing data latency. Performed advanced exploratory data analysis using Matplotlib, Seaborn, and Plotly, uncovering high-impact behavioral trends enabling targeted retention campaigns. Developed and optimized ML models including Logistic Regression, Random Forest, and XGBoost using Scikit-learn with cross-validation and hyperparameter tuning, increasing prediction precision by 20%. Led deployme

Education

Master of Science in Data Science and Statistics at Youngstown State University
August 1, 2024 - December 1, 2025

Qualifications

Add your qualifications or awards here.

Industry Experience

Software & Internet, Professional Services