ABOUT TECHNICAL BLOG TEACHING MENTORSHIP

Hi! I am Reshmi Ghosh, a Senior Applied Scientist at Microsoft Turing in the Copilot, Agents and Core org (Previously at MSAI and Microsoft AI Acceleration Program under Office of the CTO). I currently serve as a Technical Lead to drive teams to build the next generation of productivity tools that are trustworthy and efficient. I am working in the areas of long-running asynchronous agentic tasks, computer-use coding harness, safety, personalization/memory, alignment, reasoning, and trustworthy-evaluations.

Most recently I was involved in R&D and productionization of several natural language and multimodal solutions for securing Copilot reasoning and enterprise RAG from direct and indirect prompt injections and worked on several cross-organization projects related to AI security. I have also contributed towards the post-training of AI-systems for aligning with human-preferences while ensuring reliable search experiences.

I have a rich experience of delivering high-impact features/products for Fortune 500 companies and end users. I also love prototyping and working on incubation projects, a desire stemming from my past experience of finishing a forward-looking Ph.D. from Carnegie Mellon University in the intersection of deep learning, natural language processing, and renewable energy policies.

I am looking forward to continue working in fast-paced teams and across multiple areas and disciplines/roles and growing to become an empathetic product leader. Email me for an updated resume with a gsh.reshmi@gmail.com. I do not require visa-sponsorship.

Products shipped/Contributed to:

Current: Next Generation Personalization, Memory Orchestration, Long-running Tasks, Asynchronous Tasks, Reducing Over Mitigation, Mechanistic Interpretability

Last year: Security of Agentic Infrastructure, Deep Reasoning, Evaluation Framework, Coding and Artifact Generation Harness

Older: Working on Agents research and applications. Special focus on Safety and Security (Direct Prompt Injections and Cross-Domain Prompt Injections)

[Fall 2023 – Fall 2024] I had been focused on developing state-of-the-art Responsible AI and Trustworthy evaluation mechanisms for LLM and Multimodal model applications. Additionally, in 2023, I contributed to the development and shipped M365Copilot (Business Chat), followed by Azure Prompt Shields in 2024 to mitigate Cross Domain Prompt Injections.

[2021 - Spring 2023] Before joining MSAI, I was selected to be part of a coveted (~0.1% acceptance rate) AI incubation program at Microsoft’s New England Research and Development Center (NERD) (currently under the Office of the CTO, previously under Jaime Teevan’s Office of Applied Research). During this time, I shipped several products, notably:

Developed and implemented anomaly detection methods for SLA in Azure core services
Developed and deployed in production, intelligent commanding features leveraging seq2seq language model to Microsoft Office. Also prototyped a novel loss function that can predict as well as researching user preferences in UX positioning by developing a novel loss function.
Developed probabilistic graphical models to measure time saved in finding new information by knowledge workers, aiding in productivity increases through Viva Topics (see product announcement here!)
Shipped a LLM application and novel evaluation framework for generating rich-text formatting within a client application.

This work led into MSAI, where I was tech leading efforts to architect and integrate first-ever Generative AI capabilities in Microsoft’s Productivity applications (M365 CoPilots, see Satya Nadella’s announcement of these products here).

Education Background: I hold a Ph.D. from Carnegie Mellon University. I have always been passionate about applying machine learning, deep learning, economics to solving socio-technical problems, such as in the intersection of climate change and renewable energy integration.

With over 10+ years of innovating, leading, and strategizing AI solutions for nuanced user problems, I hope to continue building products and tools that can benefit the scientific community, and users equally.

Google Scholar

Github

Twitter

Nonchalant-Thoughts-at-Substack

——-

Products/Software Highlights

2026 - Memory and Copilot Personalization
- Building long-term memory systems that let Copilot retain user context across sessions while preserving privacy and trust boundaries
- Researching personalization signals that adapt agent behavior to individual users without compromising safety guardrails
- Exploring memory-grounded reasoning to reduce hallucinations and improve factual consistency in personalized agentic workflows
2025- it's becoming all about Agents
- Working with alignment issues of facts for a global audience and reduce over-refusal
- Contributed to safe release of Agentic workflows in M365 Copilots
- Learn about Agents in Copilot
2024 - Year 2 of bringing AI into search and productivity
- Working on novel post-training of AI-systems to prevent security breaches
- Azure Prompt Shields now available for third party usage. Try it now!
- Safeguarding automated search workflows from security breaches/prompt injections

Research Highlights

Search and Safety for AI
- Detecting and mitigating prompt injections hidden in images — VLMGuard (2024)
- Dataset and lessons from the 2024 SaTML LLM Capture-the-Flag Competition — NeurIPS 2024
- Are My Optimized Prompts Compromised? Exploring vulnerabilities of LLM-based optimizers — EACL 2025
Human-AI Alignment
- Bidirectional Human-AI Alignment: Emerging Challenges and Opportunities — CHI 2025
- Towards Bidirectional Human-AI Alignment: A Systematic Review for Clarifications, Framework, and Future Directions — NeurIPS 2025
- ValueCompass: A Framework of Fundamental Values for Human-AI Alignment — arXiv 2024
Interpreting and Explaining Black-box Language Models
- On Surgical Fine-tuning for Language Encoders — EMNLP 2023
- From RAGs to Rich Parameters: Probing how LLMs utilize external knowledge over parametric memory — arXiv 2024
- Quantifying reliance on external information during RAG using mechanistic analysis — BlackboxNLP @ EMNLP 2024

Updates

[June 2024]	Paper from IEEE Secure and Trustworthy ML (SatML), LLM Capture-The-Flag competition now live. Read research paper here here. We discovered that [...]
[March 2024]	Came out as silver medal winners at the IEEE Secure and Trustworthy ML (SatML), LLM Capture-The-Flag competition
[October 2023]	Paper on "Surgical Fine-Tuning" for resource efficient task-adaptation for Language encoders accepted to EMNLP 2023. Read research paper here here
[April 2023]	Invited Technical Keynote Speaker at Voices of Data Science Conferenc, University of Massachusetts, Amherst </a>
[Feb 2023]	Paper: Topic Segmentation for Unstructured Conversations accepted to IntelliSys Sept 2023. Read the Springer 'Intelligent Systems and Applications' book chapter here
[Jan 2023]	ICLR 2023, AISTATS 2023, NIPS 2022, ICCV 2022 Reviewer
[October 2022]	Paper: Topic Segmentation in the Wild: Towards Segmentation of Semi-structured & Unstructured Chats accepted to NeurIPS 2022. Read here
[Aug 2022]	NLP + Reinforcement Learning lead reviewer @ Microsoft Machine Learning, AI and Data Science Conference, Fall 2022
[July 2022]	Research paper on topic segmentation for noisy conversational datasets (from joint effort by University of Massachusetts at Amherst & Microsoft Research) under review at COLING 2022
[July 2022]	AACL 2022 and AAAI 2023 reviewer
[July 2022]	Invited Speaker at WiMLDS Bay Area to present a talk about Deep Reinforcement Learning
[May 2022]	Selected as a reviewer for evaluating research paper submitted to Microsoft's Machine Learning, AI, and Data Science journal
[April 2022]	Invited Speaker at ODSC East 2022 to present a talk about Quantization methods for large sequential models
[April 2022]	Guest Lecturer at Carnegie Mellon University, Language Technologies Institute to present a talk about Contextual Bandits & Deep Reinforcement Learning
[February 2022]	Semi-finalist at Open AI Codex challenge (selected project: Integrating Open AI to databases to accelerate database querying process for non-technical users)
[Oct 2021]	Defended Ph.D. thesis on the use of deep learning and stochastic methods to detect anomalous checkpoints in sequential electricity demand profiles.
[Jun 2021]	Selected to be part of the high coveted (0.1% acceptance rate) 2-year Applied ML research rotational program: Microsoft AI Development Acceleration Program here
[Jun 2021]	Research paper on using deep learning methods to back-forecast electricity demand accepted at ICML 2021
[Jan 2021]	Invited to be a part of the Jane Street Ph.D. Symposium and present doctoral research related to large-scale optimization of electricity grids
[Jun 2020]	Presented research poster at WindEurope Technology Workshop 2020, Naples (virtual owing to Covid restrictions) on stochastic methods in energy systems
[May 2020]	Graduated with second Master of Science degree from Carnegie Mellon University in Engineering and Public Policy
[Apr 2020]	Inducted as a part of research team at Asset Lab, University of Michigan, Ann Arbor to use stochastic methods to assess future grid reliability and also leverage advanced machine learning methods
[May 2019]	Selected to present first year doctoral work at the prestigious American Wind Energy Association (AWEA) Clean Power Expo and Conference
[Mar 2019]	Finalist at national level Yale Graduate Consulting Case competition.
[Aug 2018]	Started serving as the Vice President of CMU Graduate Consulting Club
[Mar 2018]	Elected to receive Dean's fellowship to support doctoral studies.
[Jan 2018]	Awarded doctoral fellowship by CMU Portugal, to work on the +Atlantic project - a consortium of 8 cross-functional research and academic institutions
[Dec 2017]	Graduated with a Master of Science degree in Civil and Environmental Engineering, and started working as a Research Intern with Prof. H. Scott Matthews on economic analysis and risk analysis of energy systems
[Mar 2017]	Received Merit Scholarship from Carnegie Mellon to support master's studies in the academic year 2017-2018.
[Sep 2016]	Started serving as CMU Graduate Student Advisory Committee Representative - an initiative to help bridge the gap between graduate students and the school administration.
[Jan 2016]	Received Civil and Environmental Engineering department scholarship to support master's studies for the academic year 2016-2017. Scholarship resulted in 25% tuition waiver.