About Me

I am currently a student researcher at the Johns Hopkins Center for Language and Speech Processing working on LLM reasoning, as well as a computer science student at Johns Hopkins University with a focus on Artificial Intelligence, Machine Learning, Computer Vision, and Robotics.

Projects

Transparent Reasoning with Large Language Models (Advisor: Dr. Benjamin Van Durme)

Johns Hopkins Center for Language and Speech Processing

October 2024 – Present

  • Researching social natural language inference (NLI) to improve how LLMs interpret elements like sarcasm, humor and irony.
  • Developing taxonomy of language model failure modes on dialogue-centric data, with Python and LangChain.
  • Leveraging SFT and RLFT to improve language models' abilities to create uncertainty-calibrated entailment judgements

Nuss Bar (Advisor: Dr. Peter Kazanzides)

Johns Hopkins Laboratory for Computational Sensing and Robotics

February 2024 - Present

  • 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

Technical Advisor Intern - GenAI

Scale AI

Novemeber 2024 - Present

  • 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

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 data pipeline for low-latency, asynchronous problem execution, which was used for quickly evaluating agents.

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

QAagent: A Multiagent System for Unit Test Generation via Natural Language PseudocodeProceedings Article

Deo, Akhil

In: Proceedings of the AAAI Conference on Artificial Intelligence, 2025. (Accepted for Publication)

BibTeX

Feasibility of Mobile Application for Surgical Robot TeleoperationProceedings Article

Deo, Akhil; Kazanzides, Peter

In: Hamlyn Symposium on Medical Robotics, pp. 121-122, 2023.

BibTeX

Achievements

  • 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