AI Engineer | LLM Systems, RAG & Multi-Agent Architectures | FastAPI * AWS * RL
-
17:59
(UTC -12:00) - in/sarathlingareddy754
Pinned Loading
-
vigil3d-video-inference
vigil3d-video-inference PublicEnd-to-end video violence detection system using a 3D CNN, deployed with FastAPI, Docker, AWS EC2, S3, and a React frontend on Vercel.
Python
-
Reducing-Hallucinations-with-Direct-Preference-Optimization
Reducing-Hallucinations-with-Direct-Preference-Optimization PublicAn RLHF-inspired DPO framework that explicitly teaches LLMs when to refuse, significantly reducing hallucinations.
-
Decision-Transformer-from-Scratch-HalfCheetah-Minari-BC-vs-Return-Conditioned-DT
Decision-Transformer-from-Scratch-HalfCheetah-Minari-BC-vs-Return-Conditioned-DT PublicImplementing Decision Transformers from scratch for offline RL, benchmarking return-conditioned policies against Behavior Cloning.
Python
-
VulneraAI-agent
VulneraAI-agent PublicAn agentic LLM security scanner that analyzes applications against OWASP Top 10 using tool-calling, LangGraph, and AWS Bedrock.
Python
-
-
Multi-agent-RL-texas-holdem-aec
Multi-agent-RL-texas-holdem-aec PublicAn engineering-focused multi-agent reinforcement learning system for Texas Hold'em using PettingZoo AEC and a custom PyTorch PPO self-play setup.
Python
Something went wrong, please refresh the page to try again.
If the problem persists, check the GitHub status page or contact support.
If the problem persists, check the GitHub status page or contact support.