Chintu

AI Developer / Generative AI Engineer at Bandhan Technologies (2025-04 – Present)

Architected enterprise RAG pipelines across 5 stages covering ingestion, chunking, embeddings, vector retrieval, and grounded LLM responses.
Engineered FastAPI middleware connecting 6 enterprise components spanning LLMs, databases, Jira, React, Node.js, and REST services.
Orchestrated agentic workflows across 4 control mechanisms including tool calling, function calling, structured outputs, and Pydantic validation.
Automated 5 business email processes covering notifications, approvals, reminders, summaries, and attachment handling through n8n and REST integrations.
Delivered 7 AI automation capabilities spanning self-healing operations, requirements analysis, BRD generation, user stories, workflow generation, knowledge assistance, and multi-agent orchestration.
Integrated 4 LLM provider environments across OpenAI, Azure OpenAI, Anthropic, and local model services.
Operationalized AI services across 6 production controls covering authentication, input validation, logging, monitoring, fallback handling, and audit tracking.

Data Scientist/AI Engineer at KPMG (2022-06 – 2024-08)

Fine-tuned 3 LLM families including LLaMA, Falcon, and Mistral for enterprise chatbot applications, improving response accuracy by 25%.
Engineered RAG solutions across 4 retrieval capabilities covering vector databases, embeddings, contextual retrieval, and knowledge-grounded responses, improving query accuracy by 40%.
Designed multi-agent workflows across 3 orchestration frameworks including LangGraph, CrewAI, and AutoGen for task execution and validation.
Developed AI applications across 2 delivery frameworks, FastAPI and Streamlit, reducing deployment time by 35%.
Established model evaluation practices across 3 response dimensions covering precision, consistency, and response time, reducing response time by 15%.
Partnered with data engineering and MLOps teams across 2 operational disciplines covering AI service scalability and production monitoring, increasing system throughput by 30%.

AI Engineer/ Machine Learning Engineer at Wipro Technologies (2020-08 – 2022-05)

Engineered NLP pipelines across 3 capabilities including text classification, named entity recognition, and sentiment analysis, improving model accuracy by 20%.
Developed transformer-based language services across 2 integration layers covering AI models and secure REST APIs for enterprise applications.
Standardized API response handling across 3 controls including structured JSON, schema validation, and reusable API contracts for downstream automation.
Applied transfer learning and PEFT across 2 model optimization approaches, improving model performance by 15% and reducing training time by 25%.
Engineered semantic retrieval across 2 dimensions, retrieval speed and accuracy, improving retrieval speed by 40% and accuracy by 25%.
Optimized real-time ML pipelines across 2 processing technologies, Apache Kafka and Spark, reducing latency by 35% and increasing throughput by 30%.
Automated NLP processing across 3 text-processing capabilities, reducing manual annotation effort by 43%.

Data Scientist/AI Engineer at Combino Information Technologies (2019-04 – 2020-07)

Data Scientist at Lex Nimble Solutions (2018-06 – 2019-03)

Cloud Engineer/ DevOps Engineer at Cigniti Technologies (2015-09 – 2018-05)

About