Skip to content
View Ajeenckya5's full-sized avatar

Block or report Ajeenckya5

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 is supported. 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
Ajeenckya5/README.md
Typing SVG

LinkedIn LeetCode Portfolio Email

🧠 About Me

I'm an AI/ML Engineer with an MS from UW-Madison, specializing in building production-grade LLM systems, agentic pipelines, and RAG architectures from scratch.

  • 🔬 Currently building: self-improving LLM agents with QLoRA fine-tuning and RLAIF feedback loops
  • 🏗️ I write raw API calls over frameworks — my agents don't use LangChain, AutoGen, or CrewAI
  • 🤖 Deep focus on fine-tuning, knowledge distillation, and multi-modal AI
  • 🎯 Open to: ML Engineer · AI Engineer · MLOps · Research Engineer roles

🛠️ Tech Stack

LLMs & Agents

Python PyTorch HuggingFace LlamaIndex Ollama

Vector DBs & RAG

pgvector ChromaDB Mistral LLaMA

Computer Vision & Fine-Tuning

OpenCV ViT QLoRA

Backend & Infra

FastAPI Docker PostgreSQL GitHub Actions

🚀 Featured Projects

🤖 Self-Improving LLM Agent

Grok 4 teacher → QLoRA fine-tunes LLaMA-3.2-1B student

  • ChromaDB strategy memory for cross-session learning
  • 90% task completion on Tau Bench benchmark
  • Knowledge distillation via DPO on annotated failure traces

QLoRA DPO ChromaDB LLaMA-3 Self-Improving

🖥️ CodeCraft CLI Agent

Production CLI coding agent — zero framework dependencies

  • ReAct loop + 11 workspace tools, raw HTTPS to xAI/OpenAI
  • RLAIF scoring via Grok 4 · JSONL tracing · cross-session memory
  • 7.5× faster than comparable LangChain baseline

ReAct RLAIF Tool-Calling xAI Python

📧 Multi-User Email RAG

E5-small-v2 + Mistral 7B over 10K+ indexed emails

  • JWT auth with SQL-enforced per-user isolation at pgvector layer
  • Embedding caching + batched retrieval to cut inference latency
  • Retrieval precision & answer faithfulness metrics

RAG pgvector Mistral-7B FastAPI JWT

😊 Facial Expression Recognition

CNN vs ViT transfer learning on FER2013 (7-class)

  • Comparative study: CNN baseline vs ViT vs CNN-Transformer hybrid
  • trpakov/vit-face-expression outperforms from-scratch CNN
  • Full ablation study with confusion matrices

ViT CNN PyTorch Transfer-Learning FER2013

"Build it from scratch. Understand every layer. That's how you ship reliable AI."

Profile Views

Pinned Loading

  1. CLI_AI_Agent CLI_AI_Agent Public

    Production-grade CLI coding agent built from scratch — ReAct loop, 11 tools, RLAIF scoring via Grok 4, cross-session memory, JSONL tracing. 7.5× faster than LangChain baseline.

    Python

  2. LLM_RAG LLM_RAG Public

    Multi-user email RAG: E5-small-v2 + Mistral 7B GGUF over 10K+ emails, JWT auth, SQL-enforced per-user isolation (pgvector cosine), FastAPI backend.

    Python

  3. Self_Improving_LLM_Agent Self_Improving_LLM_Agent Public

    Self-improving LLM agent: Grok 4 teacher annotates failure traces → QLoRA fine-tunes LLaMA-3.2-1B student → ChromaDB strategy memory → 90% task completion on Tau Bench.

    Python

  4. Adpative_Two-Stage_Stochastic_Routing Adpative_Two-Stage_Stochastic_Routing Public

    Adaptive two-stage stochastic optimization framework for routing under uncertainty.

    Jupyter Notebook

  5. Facial_Expressions_Recognation Facial_Expressions_Recognation Public

    FER2013 comparative study: CNN baseline vs ViT transfer learning vs CNN-Transformer hybrid. ViT (trpakov/vit-face-expression) outperforms from-scratch CNN on 7-class emotion recognition.

    Jupyter Notebook

  6. Multimodal_Optimization_Framework Multimodal_Optimization_Framework Public

    Constrained multimodal routing: MILP-based cost-time optimal paths across bus, train & flight networks. Tested on 2,040 routes from a central U.S. hub.

    Python