Shraddha Barke

My paper with @ReshabhSharma01 and @shraddha_96, “Willful Disobedience: Automatically Detecting Failures in Agentic Traces”, will appear this month in the First ACM Conference on AI and Agentic Systems (CAIS 2026). arxiv.org/abs/2603.23806

AI agents are being deployed in production, but are they safe, reliable, and trustworthy? PAgE @ PLDI'26 brings the formal methods and AI communities together to tackle this challenge! Submissions and attendance welcome. 🗓️New deadline: April 30 AoE 🔗pldi26.sigplan.org/home/page-2026

As AI agents transition from simple chatbots to complex autonomous systems, finding and fixing their errors gets harder. AgentRx is an automated diagnostic framework that pinpoints critical failures and supports more transparent, resilient agentic systems: msft.it/6012QlyiM

Sorry for not offering this earlier, but if you're a parent of a Brown student and they need help (a ride, a coffee, whatever), please email me and I'm happy to try to help. cs.brown.edu/~sk/Contact/

The Microsoft Research Undergraduate Internship Program offers 12-week internships in our Redmond, NYC, or New England labs for rising juniors and seniors who are passionate about technology. Apply by October 6: msft.it/6015scgSJ

Passionate about frontier AI models, classical symbolic reasoning, and safe/secure software? Consider applying for this position on AI-aided code analysis in my team at @GoogleDeepmind: job-boards.greenhouse.io/deepmind/jobs/…. The job is London-based, and the application deadline is July 14.

@ReshabhSharma01 , Peli de Halleux, and @shraddha_96 and I have written a new blog post, blog.sigplan.org/2025/03/20/tes…, where we say that testing AI software requires innovative new methods. #SoftwareTesting #SoftwareDevelopment #ArtificialIntelligence #SoftwareTools #LLMs #AISoftware

With Reshabh K Sharma, Peli de Halleux, and Shraddha Barke, we just released "PromptPex: Automatic Test Generation for Language Model Prompts"(arxiv.org/abs/2503.05070). Repo: github.com/microsoft/prom…. PromptPex is a tool to generate and evaluate unit tests for an AI model prompt.

Research Fellow Opportunities at Microsoft Reseach India

@RiSE_MSR is hiring summer interns next year! please reach out to chat at #NeurIPS2024 if you are interested in working at the intersection of AI/ML and FM/PL.

🌟Excited to be attending #NeurIPS2024 this year! Come find me at our poster "HySynth: Context-Free LLM Approximation for Guiding Program Synthesis" on Thursday at 4:30 pm in East Exhibit Hall A-C.

Looking for summer intern candidates interested in building tools to help author, test, debug, and deploy AI model prompts. PhD candidates with experience and skills in #ML, #RL, #NLP, #LLMs, & SE apply: lnkd.in/gAYXR9zT #AI #SoftwareEngineering #LLM #PromptEngineering

@minimario1729 Me! 🙋‍♀️

who's going to neurips next week and wants to hang out? 😄

The deadline for applications to become a student volunteer @poplconf has been extended until November 14th AOE! Please share to maximise reach :)

@davidjustodavid Congrats David!

On a personal note - I've joined the visual C++ org at Microsoft to work on ASan, the address sanitizer: a fast runtime tool for detecting memory safety errors. I'm very excited to be working within a programming languages group and to dive head first into sys programming!

In some better news… We're hiring! 📢 Join us in creating reliable, useful, and safe #AI #agents and systems.🤖 If you🩷working with awesome people in a vibrant, collaborative research lab💻, check out our opportunities below! 👇 #MicrosoftResearch #AIFrontiers @pyautogen

@RajeevAlur @KonsKallas @CIS_Penn @CS_UCLA Congratulations!!🎉

Congratulations to @KonsKallas, recent @CIS_Penn alum and now on faculty at @CS_UCLA for winning 2024 Dennis Ritchie award for best dissertation in computer systems

We are hiring for internship and full-time positions for exciting research projects, it's a great place to be!🌲 jobs.careers.microsoft.com/global/en/job/… jobs.careers.microsoft.com/global/en/job/…

I'm thrilled to share that I have joined Microsoft Research as a Senior Researcher in the amazing @RiSE_MSR team!✨Looking forward to working on AI, symbolic reasoning and human-centric methods to empower programmers and end users.

Our paper "HySynth: Context-Free LLM Approximation for Guiding Program Synthesis" is now accepted at #NeurIPS2024! HySynth presents a hybrid approach that uses LLM solutions to guide search Preprint: arxiv.org/abs/2405.15880 w/ @sakekasi @e_anaya_g @polikarn @BergKirkpatrick