About Me
I am currently a student researcher at the Johns Hopkins Center for Language and Speech Processing working on LM reasoning, as well as a computer science student at Johns Hopkins University with a focus on Natural Language Processing, Artificial Intelligence, and Machine Learning.
Projects
Transparent Reasoning with Large Language Models (Advisor: Benjamin Van Durme)
Johns Hopkins Center for Language and Speech Processing
October 2024 – Present
- Researched social natural language inference (NLI) to improve how LLMs interpret elements like sarcasm, humor and irony.
- Created SocialNLI, the first dialogue-centric social-inference dataset, comprising 243 Friends TV transcripts, 5.3K generated inferences, and a 1.4K human-annotated eval split - grounding theory-of-mind reasoning in sarcasm and irony.
- Developed efficient counterfactual-reasoning pipeline to assign calibrated plausibility scores to social inferences, surfacing latent LLM failure modes in social reasoning, using PyTorch, vLLM, Huggingface, and Langchain.
- Constructed taxonomy of language model failure modes on dialogue-centric data, with Python and LangChain.
- Leveraging process and rubric-based rewards to enhance reasoning processes in LLMs using supervised finetuning and reinforcement learning.
Nuss Bar (Advisor: Peter Kazanzides)
Johns Hopkins Laboratory for Computational Sensing and Robotics
February 2024 - July 2024
- Creating desktop planning and visualization app to aid clinicians in shaping bar for Nuss Procedure, used to correct Pectus Excavatum
- Conceiving user study comparing efficacy of Nuss bar prototypes shown in augmented reality vs. 3D printed bars
SurgiSimulate (Advisor: Dr. Peter Kazanzides)
Johns Hopkins Laboratory for Computational Sensing and Robotics
February 2022 - July 2023
- Constructed a mobile application using Swift and Objective C to control a da Vinci Research Kit (dVRK)
- Leveraged ARKit to capture transformation of mobile devices and ROS and Python for robot control
- Designed and ran a user study with 16 participants to compare performance of mobile app with existing input devices
- Presented research at the Hamlyn Symposium on Medical Robotics
Work Experience
Software Development Engineering Intern
Amazon Web Services
May 2025 - August 2025
- Designed and built a recording system capturing user interactions in browser and automatically generates reproducible workflow, improving automation accuracy by 20% and eliminating manual workflow design, using TypeScript and Python.
Technical Advisor Intern - GenAI
Scale AI
November 2024 - February 2025
- Solving Olympiad-level competitive programming (CP) problems to support training a code-reasoning LLM.
- Crafting specialized prompts enabling LLMs to solve CP problems only ∼10% of competitive programmers can solve.
Software Development Engineering Intern
Amazon AGI
May 2024 - August 2024
- Devised and developed multi-agent Small Language Model (SLM) frameworks using Amazon Nova and Anthropic Claude, achieving a ∼220% increase over baseline on the TravelPlanner dataset, which evaluates language agents’ planning abilities.
- Implemented an evaluation pipeline for multi-agent experiments with RxJava and Python, speeding up evaluations by 400%
Founding Engineer
Quantable.io
December 2023 - July 2024
- Constructed the site’s PostgreSQL database schemas and created efficient APIs in Node.js, a custom LaTeX rendering library, admin tools, and production-ready RBAC system, to serve 1,200+ quant finance problems for 2,500+ users.
Software Engineering Intern
PayPal
May 2023 - August 2023
- Redesigned monetary transactions API with an eventually consistent data strategy, caching transactions in a local database to eliminate multiple mid-tier API calls for estimate tens of thousands daily Buy Now Pay Later transactions.
- Improved API performance, reducing latency by ∼100ms per API call, leveraging Java, Spring Boot, and SQL.
Publications
SocialNLI: A Dialogue-Centric Social Inference DatasetPreprint
Deo, Akhil; Sanders, Kate; Van Durme, Benjamin
In: arXiv, 2025.
BibTeXQAagent: A Multiagent System for Unit Test Generation via Natural Language Pseudocode (Student Abstract)Proceedings Article
Deo, Akhil
In: Proceedings of the AAAI Conference on Artificial Intelligence, 2025.
BibTeXFeasibility of Mobile Application for Surgical Robot TeleoperationProceedings Article
Deo, Akhil; Kazanzides, Peter
In: Hamlyn Symposium on Medical Robotics, pp. 121-122, 2023.
BibTeXAchievements
- Pistritto Fellowship
- Pava Center for Entrepreneurship Ignite Grant
- JHU Whiting School of Engineering Undergraduate Conference Travel Grant
- JHU Student Sponsorship Initiative Award
- Ongoing Venture Prize and Most Creative Use of Twilio at HopHacks Fall 2021