Skip to content
View Keerthanareddy17's full-sized avatar
🌱
👀
🌱
👀
30 followers · 6 following

Achievements

Achievement: Pull Sharkx2

Achievements

Achievement: Pull Sharkx2

Organizations

@KJDG-KJC

Block or report Keerthanareddy17

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.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. This note will only be visible to you.
Report abuse

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

Report abuse
Keerthanareddy17/README.md
gyguygujhgukh

Hey, I'm Keerthana :)

I'm an AI/ML Engineer building systems across machine learning, deep learning agentic AI, computer vision, and data.

I've worked across 4 early-stage startups including YC-backed ProjectPro and did AI research at IIT Delhi, building production ML systems, deep-learning models, data pipelines, and research prototypes. I'm particularly interested in making AI systems more reliable, measurable, and useful in the real world.

Experience

Role Company When
Graduate Research Assistant University of North Texas June 2026 – present
AI Engineer Flawk May 2025 – May 2026
AI Research Intern Indian Institute of Technology Delhi July 2025 - December 2025
Data Science Intern ProjectPro (YC) October 2024 – April 2025
AIOps Intern ThoughtData August 2024 - February 2025
Data Analyst DeleMate March 2024 - July 2024

Currently

🛠️ Building open-source systems and experimenting with new ideas
🌱 Interested in ML engineering, agentic systems, vision applications, generative models, and reliable AI systems

My latest blog posts

I occasionally write about things I'm building and problems I'm exploring:

Let’s Talk

Whether it’s an idea, a collab, a role, or just good AI banter, I'm all ears..... let's connect ✨

Email LinkedIn

Pinned Loading

  1. foveated-vlm-search foveated-vlm-search Public

    Developed a foveated VLM search system using Qwen3-VL-2B, LoRA, vLLM, and FP8 quantization. Benchmarked 4 search strategies on 500 COCO queries; fine-tuning achieved 85.6% accuracy with 1.1% false …

    HTML

  2. spice-verified-analog-finetuning spice-verified-analog-finetuning Public

    SPICE-Verified Fine-Tuning and RL for Analog Amplifier Design : built a simulator-driven op-amp optimization agent using Qwen2.5-0.5B, LoRA fine-tuning (TRL/PEFT), and ngspice. Implemented 14 desig…

    Jupyter Notebook

  3. speech-serving speech-serving Public

    A realtime streaming speech server (Orpheus 3B on vLLM, SNAC codec, FastAPI websocket) and an audio tokenization pipeline (parquet → decode → VAD → SNAC encode → shards), built and measured on a si…

    Python

  4. AFDE AFDE Public

    AFDE is an experimental evaluation layer built on top of agent simulation outputs, with a single goal: to understand where agents fail, why they fail, and how fragile those failures are under stress.

    Python

  5. Bioflow Bioflow Public

    BioFlow is a prototype scientific data-analysis system that explores a specific ML engineering problem: turning a natural-language research question into a reliable, executable analysis workflow ov…

    Python

  6. Neural-Network-from-Scratch Neural-Network-from-Scratch Public

    This repo shows how to build a neural network from scratch, using just math, numpy and python

    Jupyter Notebook 1