Hi, my name is Harshit Soora

I'm a software engineer from College Park, Maryland — building scalable cloud, AI and HPC systems.

Let's work together.

From cloud-native infrastructure and AI inference platforms to HPC workflow tooling and full-stack web applications. I help ambitious teams ship reliable systems at scale — the more interesting the constraints, the better.

About my approach

Experience

A few places I've shipped work.

  1. Google Upcoming · Joining soon Next

    Software Engineer

    Joining Google as a Software Engineer following my graduate studies at UMD. More to come.

  2. Open OnDemand Oct 2024 — Present Graduate Research Assistant

    Software Developer · Graduate Research Assistant

    Architecting a Workflow Manager for Open OnDemand (700+ HPC sites), letting researchers visually design DAG-based computational pipelines with conditional branching and real-time job reporting. Leading development under NSF grant #2411376 with the Ohio Supercomputer Center and Texas A&M.

    • Ruby
    • HPC
    • Apptainer
    • Slurm
    • DAGMan
    • Airflow
  3. Inovalon Jun 2025 — Aug 2025 Internship · Bowie, MD

    Software Developer Intern

    Built an AI-powered SOAP notes platform for healthcare clients — NLP-based auto-suggestions and real-time duplicate detection cut development time ~40%. Architected an automated approval workflow on Azure with email orchestration and role-based routing, with 95% code coverage end-to-end and savings of ~$100K in manual processing.

    • C#
    • ASP.NET
    • Azure
    • SQL
    • JavaScript
  4. NVIDIA Jul 2021 — Aug 2024 Full-time · Pune, India

    Software Engineer II — Cloud & AI

    Architected AI inference infrastructure for Maxine Audio NIMs on Triton Inference Server & NVCF. Designed a bidirectional streaming SDK in C++ that cut model serving latency ~40% and enabled real-time audio. Co-invented an AI-powered audio editor with prosody preservation hitting ~20ms latency. Engineered GeForce NOW cross-platform stacks across Android, iOS, macOS and Linux, improving streaming QoS ~30%. Built observability with Kafka, Prometheus and Kibana, enabling 50–60% faster debug.

    • Go
    • C++
    • Python
    • Java
    • Kafka
    • Prometheus
    • RTP

Open Source.

Side projects, research and experiments I've put out into the world. A few favourites below.

  1. 01 Evaluation Framework 2025

    UniBench.

    A universal evaluation framework for software engineering agents on issue resolution and test generation tasks. Proposes 4 novel metrics — null-resolution, edit-resilience, error-resolution@x and line-level fault localization — to measure fine-grained code reasoning beyond pass@k.

    The pipeline runs CodeActAgent over 2,294 GitHub issue–PR pairs, comparing 15+ benchmarks (SWE-Bench, HumanEval, BigCodeBench, MBPP).

    • Python
    • LLM Agents
    • CodeActAgent
    • SWE-Bench
    • Evaluation
    Get UniBench
  2. 02 Security Tooling 2025

    Vulineage.

    A web tool that reconstructs Docker image tag hierarchies and overlays vulnerability timelines, helping teams pick safer base images 3–4× faster than existing tools.

    Built with interactive D3.js dashboards (icicle plots, force-directed graphs, time-series) on a Python backend hosted on AWS.

    • JavaScript
    • D3.js
    • Python
    • AWS
    • Information Viz
    Open Vulineage
  3. 03 Reinforcement Learning 2021

    Carla-DDPG.

    Bachelor's thesis on safe strategies for autonomous driving. Hierarchical program-controlled RL with maneuver-specific DDPG agents (lane-swap, obstacle avoidance) — 58.2% sample-efficiency improvement over flat DRL.

    Validated on 10 NHTSA pre-crash scenarios in CARLA with 5 LTL safety specifications across 18,477 clauses.

    • Python
    • PyTorch
    • Keras
    • DDPG / PPO
    • CARLA
    Get Carla-DDPG

Publications

Things I've written.

Peer-reviewed work and pre-prints — drawn from my research at IIT Kharagpur and the University of Maryland.

  1. 01 arXiv · cs.AI 2025

    From SWE-Bench to Universal Benchmarking: Evaluating Code-Acting LLM Agents.

    Harshit Soora et al.

    Proposes a universal evaluation framework for code-acting LLM agents on issue resolution and test-generation tasks, introducing four novel metrics — null-resolution, edit-resilience, error-resolution@x and line-level fault localization — that measure fine-grained reasoning beyond pass@k. Pipeline runs CodeActAgent over 2,294 GitHub issue–PR pairs across 15+ benchmarks.

    Read on arXiv
  2. 02 arXiv · cs.RO / cs.LG 2021

    Hierarchical Program-Triggered Reinforcement Learning Agents For Automated Driving.

    Briti Gangopadhyay, Harshit Soora, Pallab Dasgupta.

    Hierarchical program-controlled reinforcement learning for autonomous driving — a structured controller invokes maneuver-specific DDPG agents (lane-swap, obstacle avoidance) to deliver a 58.2% sample-efficiency improvement over flat DRL. Validated on 10 NHTSA pre-crash scenarios in CARLA with 5 formally verified LTL safety specifications across 18,477 clauses.

    Read on arXiv

Coursework & Projects

What I've studied.

Graduate and undergraduate coursework that's shaped how I build things — across AI, systems, and theory — alongside the class projects that came out of them.

University of Maryland, College Park

M.S. in Computer Science · GPA 3.94 / 4.0 · Aug 2024 — May 2026

  • 01 Natural Language Processing
  • 02 Reinforcement Learning for Robotics
  • 03 Generative AI Agents (Agentic AI)
  • 04 Information Visualization
  • 05 Parallel Computing
  • 06 Computer Vision

IIT Kharagpur

B.Tech (Hons.) Computer Science & Engineering · CGPA 8.37 / 10 · Jul 2017 — May 2021

  • 07 Algorithms
  • 08 Software Engineering
  • 09 Computer Networks
  • 10 Database Management Systems
  • 11 Operating System
  • 12 Object Oriented System Design
  • 13 Distributed Systems & Cloud Computing

Class projects

Built along the way.

  • 01 University of Maryland Jan 2025 — May 2025

    Vulineage — Docker Image Security Visualizer

    Web-based security visualization that reconstructs Docker image tag hierarchies and overlays vulnerability timelines. Built interactive D3.js dashboards (icicle plots, force-directed graphs, time-series) on a Python backend hosted on AWS, enabling real-time querying of Docker tag lineage and CVE distributions.

    • JavaScript
    • D3.js
    • AWS
    • Python
    • Information Viz
  • 02 IIT Kharagpur · Bachelor's Thesis Jan 2020 — May 2021

    Safe Strategies for Autonomous Driving (Carla-DDPG)

    Hierarchical Program Controlled RL with maneuver-specific DDPG agents (lane-swap, obstacle avoidance), achieving 58.2% sample-efficiency improvement over flat DRL. Validated on 10 NHTSA pre-crash scenarios in CARLA with 5 formally verified LTL safety specifications across 18,477 clauses.

    • Python
    • PyTorch
    • Keras
    • DDPG / PPO
    • CARLA
  • 03 IIT Kharagpur · Distributed Systems Jan 2021 — May 2021

    Ceph-Inspired Distributed Storage System

    Architected a fault-tolerant distributed storage system with a Metadata Server (MDS) and Monitor servers, primary–backup replication across four Object Storage Devices on AWS S3. Implemented a Cassandra-inspired consistency model with passive replication, heartbeat monitoring and Dynamo's gossip protocol — 99.9% data availability with sub-2-second failure detection.

    • Python
    • AWS
    • MySQL
    • Sockets
    • Distributed Systems
  • 04 IIT Kharagpur · Network Security Aug 2020 — Dec 2020

    Secure File Transfer over Cloud

    Engineered a secure cloud platform implementing hybrid encryption combining Elliptic Curve Cryptography with pseudo-randomly generated symmetric keys to prevent man-in-the-middle attacks. Custom N-part file sharding with layered encryption improved security 3–4% over existing approaches.

    • PHP
    • Python
    • OpenStack
    • GCP
    • Cryptography