Neelesh K Shukla

Neelesh K Shukla

Principal Applied Scientist | Applied Sciences Lead – GenAI & Advanced AI @ Oracle | xHead - AI Research and Innovation - State Street | Research Fellow | IIT Guwahati (Rank 1)

GenAI · Agentic AI · Reasoning · NL2SQL · SLMs · Learning from Feedback

Advancing next-generation GenAI through research and enterprise-scale AI systems for reasoning, retrieval, NL2SQL, agentic memory, and Agentic AI — with a focus on scalable SLMs, feedback-driven learning, grounded reasoning, and non-sycophantic alignment.

Explore highlights of work Research Console
15+ Years
13 Publications
9 Patents (4 granted)
#1 IITG Rank
research_console

$ cat active_research_topics

reasoning Enterprise reasoning architectures and knowledge grounding
retrieval Retrieval-augmented generation at scale
nl2sql NL2SQL and structured data reasoning
agentic Agentic AI memory, orchestration and autonomy
slm Small Language Models for enterprise efficiency
Learning from feedback without sycophancy

$ echo $CURRENT_FOCUS

Enterprise-grade GenAI grounded in reasoning, retrieval, NL2SQL, Agentic AI, SLMs, and learning from feedback — no sycophancy.

$ _

Short Bio

Neelesh is a Principal Applied Scientist and Applied Sciences Lead at Oracle Generative AI, specializing in Generative AI, Natural Language Processing (NLP), Large Language Models (LLMs), and intelligent enterprise AI systems. With over 15 years of experience spanning scientific research, applied AI, and large-scale production systems, he leads applied science and research initiatives focused on enterprise-scale AI architectures for reasoning, retrieval, NL2SQL, agentic systems, and evaluation-driven AI. His work centers on building reliable, scalable, and production-grade AI systems grounded in scientific rigor and real-world deployment.

Before joining Oracle, he spearheaded AI research and innovation at State Street, advancing the adoption of Generative AI and intelligent enterprise systems across financial services. His research focuses on Document Intelligence, Machine Reading Comprehension, Retrieval-Augmented Generation (RAG), Visual NLP, learning with limited labeled data, and enterprise-grade NL2SQL systems.

He contributes to AI research community through publications and by serving as a reviewer for leading conferences and journals including ACL ARR and venues, EMNLP, AACL, and IEEE venues.

Neelesh holds an M.Tech in Computer Science and Engineering from IIT Guwahati, where he graduated as Department Rank 1. He was also selected for the Government of India's prestigious international master's fellowship program associated with Heidelberg University, Germany.

Highlights

Enterprise NL2SQL Orchestration

Semantic schema linking, ambiguity resolution, grounded generation, and production constraint handling for natural language to SQL at scale.

Schema Linking Grounding Reasoning

RAG Evaluation Framework

Retrieval diagnostics, grounding analysis, hallucination tracing, and enterprise-grade evaluation loops for production RAG systems.

Retrieval Evaluation Safety

Agentic AI Systems

Conversation memory architectures, tool-use orchestration, multi-agent coordination, and autonomous reasoning for enterprise AI workflows.

Agentic AI Memory Orchestration

Document Intelligence Pipeline

Multimodal document understanding, PDF parsing, layout analysis, and cross-lingual extraction for complex business documents.

Multimodal PDF NLP

Small Language Model Architecture

Efficient SLM design for enterprise deployment: distillation, quantization, pruning, and task-specific fine-tuning with minimal compute footprint.

SLMs Distillation Efficiency

Learning from Feedback & Alignment

RLHF, preference optimization, reward modeling, and anti-sycophancy techniques for next-gen GenAI that learns reliably from human feedback.

RLHF Alignment No Sycophancy

Publications

Google Scholar DBLP ACL Anthology
'26
Annotating Indian Regional Biases using Large Language Models: Evaluation and Analysis [Accepted] Debasmita Panda, Akash Anil, Neelesh Kumar Shukla The 15th Joint Conference on Lexical and Computational Semantics colocated ACL 2026
'25
IndRegBias: A Dataset for Studying Indian Regional Biases in English and Code-Mixed Social Media Comments Debasmita Panda, Akash Anil, Neelesh K. Shukla arXiv preprint arXiv:2601.06477
arXiv
'25
Ontology-Driven Multimodal Framework for Automated Interpretation of Architecture Diagrams Sakthivel Thangaraj, Neelesh K. Shukla, Viji Krishnamurthy IEEE Big Data 2025
IEEE
'25
RAG-CUE: Actionable and Unified Evaluation for Retrieval-Augmented Generation Systems Prabhat Kumar Prabhakar, Neelesh K. Shukla, Viji Krishnamurthy IEEE Big Data 2025
IEEE
'25
GraphRAG Analysis for Financial Narrative Summarization Neelesh Kumar Shukla, Prabhat Prabhakar, Sakthivel Thangaraj et al. FinNLP/FNP @ ACL 2025
ACL
'25
KULFi: Knowledge Utilization for Optimizing LLMs for Financial Causal Reasoning Neelesh Kumar Shukla, Sandeep Singh, Prabhat Kumar Prabhakar et al. FinNLP/FNP @ ACL 2025
ACL
'24
T2I-RISE: Text-to-Insights with Reinforcement Learning, Semantic Layers and Enrichment Raghu Katikeri, Sai Phaniraja, et al. IEEE Big Data 2024
IEEE
'23
Investigating LLMs for Financial Causality Detection in Multilingual Setup Neelesh K. Shukla, Raghu Katikeri, Msp Raja et al. IEEE Big Data 2023
IEEE
'23
Generative AI Approach to Distributed Summarization of Financial Narratives Neelesh K. Shukla, Raghu Katikeri, Msp Raja et al. IEEE Big Data 2023
DOI
'22
DoSA: Accelerating Annotations on Business Documents with Human-in-the-Loop Neelesh K. Shukla, Msp Raja, Raghu Katikeri, Amit Vaid ACL DASH 2022
ACL
'22
DiMSum: Distributed and Multilingual Summarization of Financial Narratives Neelesh K. Shukla, Amit Vaid, Raghu C Katikeri et al. FNP 2022
ACL
'20
Improving Text-Code Pair Quality Using Function Calls and API Documentation Diego Costa, Neelesh K. Shukla, Prof. Dr. Artur Andrezak (Guide) MSR 2020 (Short Paper)
'18
Inclusion of Role into Named Entity Recognition and Ranking Neelesh Kumar Shukla, Prof. Dr. Sanasam Ranbir Singh (Guide) Master's Thesis 2018
arXiv

Patents

'25
Staggered-Sampling Technique for Detecting Sensor Anomalies in a Dynamic Univariate Time-Series Signal Neelesh Kumar Shukla, Saurabh Thapliyal, Matthew T. Gerdes, Guang C. Wang, Kenny C. Gross US Patent 12,260,304 · Oracle
USPTO
'24
Hyper Parameter Tuning for Machine Learning Models Suresh Kumar Golconda, Vijayalakshmi Krishnamurthy, Someshwar Maroti Kale, Sujay Sarkhel, Nickolas Kavantzas, Mohan U. Kamath, Neelesh Kumar Shukla, Vidya Mani, Amit Vaid US Patent 12,086,725 · Oracle
USPTO
'24
Automated Correlation Analysis and Self-Regulation of Attributes S Mahishi, Suresh Kumar Golconda, V Mani, K Gontla, Neelesh K. Shukla, A Vaid US Patent 20240330400 · Oracle
USPTO
'20
Generating a Recommended Shaping Function to Integrate Data Within a Data Repository M Bhide, S Gudla, S Mehta, P Rateria, S Shaikh, NK Shukla, PS Taylor US Patent 10,783,161 · IBM
USPTO

Experience

Jun 2024 – Present Oracle

Principal Applied Scientist / Applied Sciences Lead — GenAI & Advanced AI

Leads applied science for GenAI and Advanced AI products at Oracle. Drives enterprise-grade AI systems grounded in retrieval, reasoning, orchestration, and rigorous evaluation. Earlier built Automated ML platform and owned IoT Analytics offerings.

Oct 2021 – Jun 2024 State Street

Senior Manager, AI Group & Head — AI Innovation & Research

Incubated and led AI Research & Innovation, driving NLP and GenAI research for financial applications. Published 4 papers in 2 years. Led GenAI adoption in the Alpha Data Platform for investment management.

Jun 2018 – Oct 2021 Oracle

Senior Data Scientist (SMTS)

Built Automated ML platform, owned IoT Analytics (predictive analytics, anomaly detection), initiated research collaborations with Oracle Labs. Built end-to-end ML pipelines on Spark/Big Data.

Jan 2018 – Mar 2018 Heidelberg University

Visiting Research Fellow — PVS Lab

Govt of India Masters' Fellowship. Worked with Prof. Artur Andrzejak on code snippet extraction at Parallel and Distributed Systems Group.

May 2017 – Jul 2017 IBM Research

Research Intern — Watson Data Platform

Enhanced Watson Data Platform with cognitive support features. Developed Shaping Function and Next Action Recommendation using deep learning and data mining.

Oct 2014 – Jul 2016 Landis+Gyr (Toshiba Group)

Senior Software Engineer — IoT Energy Management

Built IoT-based Intelligent Energy management product. Owned text search, load forecasting ML, and application backend. Led team of 6.

Jun 2012 – Oct 2014 DXC Technology

Product Developer — Banking Product

Engineered middleware layer for Accounts and Cards modules of Celeriti Banking Product.

Dec 2009 – Jun 2012 Tata Consultancy Services

Systems Engineer

Led middleware development for Global Procurement, Employee Performance, and Recruitment systems. Managed 7-member team. Architected Vendor Management System.

Professional Service & Editorial Contributions

'26
Technical Reviewer — Building Generative AI for Enterprise: A Practical Guide to Developing GenAI Systems to Solve Business Problems BPB Publications · ISBN-13: 978-9378541353 Reviewed technical content covering enterprise Generative AI, LLM applications, RAG architectures, agentic workflows, deployment strategies, evaluation methodologies, and production-grade AI systems.
View Book
Ongoing
Conference and Journal Reviewer ACL ARR, EMNLP, AACL, IEEE Conferences and related NLP/AI venues.

Talks

'25
Gen-AI: Challenges and How to Move Forward DSE Day @ IISER Bhopal
Report
'23
Investigation of LLMs for Financial Use Cases NLP Summit 2023
Talk Page
'22
Challenges in Financial Document Understanding – NLP and Beyond NLP Summit 2022
Talk Page

Education

M.Tech Computer Science & Engineering

IIT Guwahati

Department Rank 1 · CGPA 9.7/10
Thesis: Entity Role Detection in Attack Events

Research Fellowship

Heidelberg University, Germany

Govt of India Masters' Fellowship
PVS Lab · Prof. Artur Andrzejak

B.Tech Computer Science

MMM Engineering College

Awards & Honors

2023 Best Work — Financial Narrative Summarization Task IEEE BigData Conference
2022 Standing Ovation — Top Employee Award State Street
2022 2nd Best Work — Financial Narrative Summarization LREC 2022 · 1st in Greek
2018 Joint Ph.D. Position Offer IIT Guwahati · Heidelberg University, Germany
2018 Rank 1 — M.Tech Computer Science & Engineering IIT Guwahati (CGPA 9.7/10)
2018 Joint Research Fellowship Govt of India · Heidelberg University