Vedant Agarwal

Work

I’m an engineer at Prentis. Here’s what I’ve worked on.

↗ resume.pdf·github·linkedin·email

$ ./nowlive

Prentis

Early Engineer, Forward-Deployed · Feb 2026 → present

San Francisco · on-site with enterprise customers

Prentis is a computer use lab founded by Reid Hoffman and Mark Pincus. I am one of the first engineers, working forward-deployed on customer deployments in healthcare billing and supply chain.

  • Healthcare billing (RCM). Deployed an end-to-end multi-agent platform that works insurance claims on its own. An LLM orchestration layer loads claim state, plans the next action, and dispatches to specialized agents, running on Temporal with Redis-backed distributed locking and retry for multi-call campaigns.
  • Voice. Live payer calls on ElevenLabs Conversational AI and Telnyx SIP, with claim context injected at dial time and structured outcomes parsed back out of the transcripts.
  • Browser. Vision-language agents on Playwright that drive payer portals (Availity, Kern), fill multi-step forms, and clear MFA programmatically through the Microsoft Graph API.
  • Supply chain automation. Order-processing agents integrated into a legacy ERP pipeline for large customers, owning the customer relationship through rollout.
TypeScriptPythonTemporalRedisPostgresPlaywrightVLMsElevenLabsTelnyx SIPMicrosoft GraphDockerAWS

#previously

past full-time and internships, newest first.

  1. RunAnywhere (YC W26) · Software Engineer Intern

    Dec 2025 – Feb 2026

    San Francisco, CA

    Local-first inference SDK for running real models in the browser and on the edge instead of the data center.

    • Extended the core inference SDK with multi-provider model routing, optimized tokenization, and request batching. LoRA-fine-tuned models down to a footprint that fits edge devices.
    • Built the on-device browser agent: VLM-driven web automation in a Chrome extension with Transformers.js, ONNX runtime over CDN, and a state-machine-first architecture that survives restricted pages and MV3 CSP.
    • Shipped Android Use Agent into the SDK Playground: VLM-on-Android wired into a real interaction loop, plus x86_64 ABI support so it runs on emulators, not just hardware.
    • Cross-platform Playground (Swift + Android + on-device browser) so partners and customers could touch the SDK without standing up infra.

    merged into RunanywhereAI/runanywhere-sdks

    shipped in RunanywhereAI/on-device-browser-agent

    TypeScriptSwiftKotlinWebGPUTransformers.jsONNXVLMsPyTorchLoRA

  2. Tegore-AI (YC X25) · Software Engineer Intern

    Oct 2025 – Dec 2025

    San Francisco, CA

    AI tutoring that draws on a whiteboard mid-conversation. Voice and text in the same session, sharing state.

    • Designed an LLM tool-calling architecture that dynamically renders interactive React components mid-conversation, so the tutor can draw a diagram or quiz the student without leaving the chat.
    • FastAPI / TypeScript / Postgres backend with prompt-chaining, contextual retrieval, and concurrent workers. +27% tutor accuracy, −35% latency.
    PythonTypeScriptFastAPIPostgresOpenAIElevenLabsCartesia

  3. The Mind Company · Machine Learning Engineer Intern

    Sep 2024 – Dec 2024

    San Jose, CA

    Real-time brain-computer interface: EEG signals to motor-imagery control, sub-50ms.

    • CNN + Common Spatial Patterns classifier hit 92% on a 4-class motor imagery task. INT8 quantization let it run on a Raspberry Pi at sub-50ms inference.
    • Rebuilt the signal-processing pipeline with ICA artifact rejection and adaptive bandpass filtering, for +12 dB SNR. Mixed-precision PyTorch training cut iteration time 3×.
    PythonPyTorchNumPyEEG / DSPRaspberry PiQuantization

# say hi

building something where this résumé would be useful?

i'm most useful around multi-agent systems, voice + browser automation, and infra for AI that has to actually run in production. write to me.

send me an email