Skip to content
View Sashi445's full-sized avatar

Block or report Sashi445

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 userโ€™s behavior. Learn more about reporting abuse.

Report abuse
Sashi445/README.md

Hi, I'm Sashidhar Motte ๐Ÿ‘‹

Applied AI Engineer | Full-Stack Developer | Digital Craftsman

Currently pursuing my Master's in Computer Science at the University at Buffalo (Graduating June 2026).

I build intelligent systems that solve real problems, combining deep expertise in AI/ML with full-stack development to create products people love. From ideation to deployment, I craft experiences that blend innovation with practicality.


๐Ÿš€ Technical Expertise

  • AI/ML: Reinforcement Learning (RL), Natural Language Processing (NLP), Computer Vision, Fine-tuning LLMs, CLIP, SAM, InsightFace.
  • Engineering: Python, PyTorch, FastAPI, LangChain, LlamaIndex, SQL, MLOps, Docker.
  • Frontend: React, Next.js, Tailwind CSS, Chakra UI, Framer Motion.

๐Ÿ› ๏ธ Featured Projects

Enhanced the fact-checking capabilities of Large Language Models by implementing RL loops to verify and ground model outputs against factual datasets.

๐Ÿ–ผ๏ธ Face Studio & Image Indexing

Built a comprehensive face recognition and clustering pipeline using InsightFace and DBSCAN. Developed a system for image feature extraction and knowledge graph creation using CLIP and custom-trained VLMs.

Built a custom STT engine and an English-to-French translation model from scratch, including a video captioning systemโ€”all without relying on external APIs.


๐Ÿ“ˆ Currently Exploring

  • Multi-agent systems and autonomous LLM workflows.
  • Unsupervised face clustering and large-scale image feature indexing.
  • Advancements in Computer Vision (SAM 2, Depth Estimation).

๐Ÿ’ป Technical Skills

Category Technologies
Languages C, C++, Java, Python, JavaScript, SQL
Frontend ReactJS, Redux, Next.js, TypeScript, TailwindCSS, GSAP, Vite
Backend NodeJS, ExpressJS, Spring Boot, FastAPI, Kafka, MongoDB
Big Data & ML PyTorch, TensorFlow, Spark, Hadoop, LangChain, LlamaIndex
Tools & Platforms Linux, Docker, AWS, Git/GitHub, CI/CD, MLOps

๐Ÿ“ซ Connect with Me


"From ideation to deployment, I craft experiences that blend innovation with practicality."

Pinned Loading

  1. speech_to_text_dl speech_to_text_dl Public

    Jupyter Notebook 1

  2. search-r1-implementation-RL search-r1-implementation-RL Public

    Jupyter Notebook