Skip to content
View swappysh's full-sized avatar

Block or report swappysh

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don't include any personal information such as legal names or email addresses. Markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
swappysh/README.md

Swapnil Sharma

AI/ML engineer focused on production LLM systems, multi-agent architectures, and evaluation infrastructure.

Currently at Aleph building an agentic FP&A assistant — agent capabilities, LLM-as-a-judge evals, and production reliability on Google ADK.

Previously at HippocraticAI as a founding team member — co-built the Polaris multi-agent constellation for safety-critical patient voice AI, scaled to 1M+ calls/week, led LLM fine-tuning (70B–405B, QLoRA).

Building on the side: lekh.space — private encrypted writing vault; an MBTI-aware voice journaling app (LiveKit, Gemini); and Beacon, an emoji-only messenger.

Website · LinkedIn · Twitter

Pinned Loading

  1. language_modeling_via_stochastic_processes language_modeling_via_stochastic_processes Public

    Forked from rosewang2008/language_modeling_via_stochastic_processes

    Language modeling via stochastic processes. Oral @ ICLR 2022.

    Python

  2. SeedlingClassification SeedlingClassification Public

    Jupyter Notebook 1

  3. lekh lekh Public

    JavaScript 1