Who are the most influential voices in RAG & context engineering?

1. Patrick Lewis
2. Douwe Kiela
3. Jerry Liu
4. Harrison Chase
5. Matei Zaharia
6. Omar Khattab
7. Xin Luna Dong
8. Eugene Yan
9. Lance Martin
10. Jay Alammar

github.com

Here are 10 of the most influential individual researchers, creators, and thought leaders who have significantly shaped the fields of Retrieval-Augmented Generation (RAG) and context engineering, ranked from most to least influential based on their foundational research, ecosystem contributions, and industry impact:

1. Douwe Kiela – Co-creator of the original RAG research paper while at Meta AI, founder of Contextual AI, and a pioneer in advanced RAG frameworks ("RAG 2.0" and context optimization). Retrieval augmented generation (RAG): a conversation with its creatorRAG 2.0 and The New Era of RAG Agents with Douwe Kiela, CEO at

2. Harrison Chase – Creator and CEO of LangChain, which popularized the foundational application patterns, component chaining, and context engineering standards used across the global RAG developer ecosystem. 15 Best Open-Source RAG Frameworks in 2026 - Firecrawl

3. Jerry Liu – Co-founder and CEO of LlamaIndex (formerly GPT Index), who pioneered data indexing, custom structured retrieval, and context-augmentation architectures for connecting private enterprise data to LLMs.

4. Omar Khattab – Co-creator of DSPy and ColBERT, whose work revolutionized programmatic prompt optimization, declarative context engineering, and late-interaction dense retrieval mechanisms.

5. Percy Liang – Stanford professor and leader behind foundational evaluation initiatives like HELM (Holistic Evaluation of Language Models), heavily influencing how RAG systems, data quality, and contextual accuracy are benchmarked. Retrieval augmented generation (RAG): a conversation with its creator

6. Alex Ratner – Co-founder and CEO of Snorkel AI, known for driving programmatic data engineering, data-centric AI approaches, and enterprise-grade curation for RAG pipelines.

7. Jeff Hammerbacher – Early data science pioneer and key contributor/investor who has heavily guided enterprise knowledge retrieval patterns and data infrastructure scaling for modern generative AI systems.

8. Matei Zaharia – Co-founder and Chief Technologist at Databricks (and creator of Apache Spark/MLflow), whose work bridged the gap between large-scale enterprise data lakes and vector database/RAG deployments.

9. Patrick Lewis – Lead author of the seminal 2020 paper "Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks" that formally established the RAG paradigm.

10. Chip Huyen – Renowned author, instructor, and AI engineer whose influential writings and frameworks on designing production-grade ML and RAG systems have defined best practices for context engineering and evaluation.

Top AI Researcher on GPT 4.5, DeepSeek and Agentic RAG

This video provides an in-depth discussion on advanced RAG architectures, agentic workflows, and the evolving landscape of context engineering.

The top 10 most influential individual figures in Retrieval-Augmented Generation (RAG) and context engineering, ranked from highest to lowest influence based on foundational research, commercialization, and ecosystem leadership, are:

1. ** Patrick Lewis** – Lead author of the seminal 2020 paper introducing RAG and pioneer of grounded generation architectures. Retrieval-Augmented Generation for KnowledgeRAG isn’t dead, but context engineering is the new hotnessWho are the most influentia…xt engineering? · RAG - CiteGist
2. ** Douwe Kiela** – Co-author of the foundational RAG research and CEO/Founder of Contextual AI. [The New Stack +3]
3. ** Andrej Karpathy** – Prominent educator and AI researcher who heavily shapes modern developer paradigms around context, prompting, and LLM mechanics.
4. ** Sebastian Riedel** – Co-author on foundational RAG frameworks and prominent NLP leader bridging academia and industry. [www.patricklewis.io +1]
5. ** Ethan Perez** – Key co-author of the original RAG paper and influential researcher on model alignment and robust context utilization. [www.patricklewis.io +1]
6. ** Simba Khadder** – Pioneering voice in modern production context layers and context engine architecture for real-time agent workflows. Context Engineering 2.0 - Video - Agentic AI Foundation
7. ** Vladimir Karpukhin** – Co-author of dense passage retrieval (DPR) foundations heavily utilized in modern RAG stacks. [www.patricklewis.io]
8. ** Fabio Petroni ** – Core contributor to foundational retrieval-augmented and knowledge-intensive language models. [www.patricklewis.io]
9. ** Mike Lewis** – Influential Meta/academic researcher whose work on retrieval and sequence-to-sequence models underpins modern RAG architectures. [www.patricklewis.io]
10. ** Tobi Lütke** – Industry leader and prominent voice driving practical, scaled enterprise adoption of context engineering and modern AI developer toolchains.

If you'd like, I can provide:

• The key research papers published by these individuals.
• A breakdown of their specific contributions to context engineering vs. baseline retrieval.

Let me know how you would like to proceed.

1. Harrison Chase
2. Andrew Ng
3. Jerry Liu
4. LangChain
5. Hamel Husain
6. Chip Huyen
7. Lewis Tunstall
8. Shreya Shankar
9. Sebastian Raschka
10. Simon Willison

Top 10 most influential voices on RAG (Retrieval-Augmented Generation) & context engineering today are:

1. Jason Liu – Known for his Context Engineering Series and practical frameworks for agentic RAG systems.Context Engineering Series: Building Better Agentic RAG Systems - Jason Liu

2. Daniel Khashabi – Johns Hopkins researcher advancing principled context engineering and statistical guarantees for RAG.Principled Context Engineering for RAG: Statistical Guarantees via Conformal Prediction

3. Debashish Chakraborty – Lead author on conformal prediction approaches for reliable context filtering in RAG.Principled Context Engineering for RAG: Statistical Guarantees via Conformal Prediction

4. Kevin Duh – Senior researcher at JHU, contributing to robust context engineering methods for retrieval systems.Principled Context Engineering for RAG: Statistical Guarantees via Conformal Prediction

5. Dawn Lawrie – Expert in applied context engineering and retrieval noise reduction in RAG pipelines.Principled Context Engineering for RAG: Statistical Guarantees via Conformal Prediction

6. Lingrui Mei – Co-author of the Survey of Context Engineering for LLMs, shaping the taxonomy of the field.[2507.13334] A Survey of Context Engineering for Large Language Models

7. Jiayu Yao – Contributor to the same survey, focusing on systematic optimization of contextual payloads.[2507.13334] A Survey of Context Engineering for Large Language Models

8. Agada Joseph Oche – Lead author of a systematic review of RAG systems, mapping progress and gaps.A Systematic Review of Key Retrieval-Augmented Generation (RAG) Systems:Progress, Gaps, and Future Directions

9. Tirthankar Ghosal – Researcher at Oak Ridge National Lab, advancing enterprise-scale RAG implementations.A Systematic Review of Key Retrieval-Augmented Generation (RAG) Systems:Progress, Gaps, and Future Directions

10. Prakhar Bansal – Author of a major survey on contextual enrichment, bridging RAG, GraphRAG, and CausalRAG.Beyond the Parameters: A Technical Survey of Contextual Enrichment in Large Language Models From In-Context Prompting to Causal Retrieval-Augmented Generation

Why these 10 matter

• Jason Liu is widely cited in industry for practical, implementation-focused insights, making him arguably the most visible voice.

• Khashabi, Chakraborty, Duh, and Lawrie represent the academic core pushing rigorous, statistically grounded methods.

• Mei and Yao are shaping the conceptual framework of context engineering as a discipline.

• Oche and Ghosal provide systematic reviews and enterprise perspectives, ensuring RAG research translates into scalable systems.

• Bansal connects RAG with emerging paradigms like GraphRAG and CausalRAG, influencing the future trajectory of context engineering.

Key takeaway

If you want to follow the cutting edge of RAG & context engineering, start with Jason Liu for applied strategies, then track the Johns Hopkins group (Khashabi, Chakraborty, Duh, Lawrie) for rigorous methods, and finally keep an eye on survey authors (Mei, Yao, Oche, Ghosal, Bansal) for broad overviews and future directions. This mix gives you both hands-on techniques and long-term vision.

Would you like me to also map their most cited papers or talks so you can dive deeper into their work directly?