Building production AI systems — multi-agent pipelines, LLM safety, and real-time voice AI.
- 🔭 I'm currently working on AI Agents, RAGs, and LLMs
- 🌱 I'm learning System Design, Distributed Systems, Concurrency, Backend Engineering, and AWS
- 💬 Ask me about AI Safety & Evals, Multi-Agent Systems, LLMs, RAG pipelines, or Backend Engineering
- 🎯 2026 Goal: Break into AI/ML engineering and ship a production agent system at scale
- ⚡ Fun fact: Big Tennis and Chess enthusiast — I'll happily watch a 6-hour live chess stream
Languages
AI / ML
Safety & Evals
Systems & Infra
Databases & Tools
| Project | Description | Stack | Link |
|---|---|---|---|
| 🔐 SentinelMesh | Policy-enforced multi-agent orchestration with a custom Go Deep Prompt Inspection proxy — blocks prompt injection, PII leakage, and RBAC violations in real time | LangGraph, Go, ChromaDB, FastAPI, Docker | Repo |
| 🚨 Incident Response System | Fully autonomous AI pipeline that diagnoses production errors, generates & tests code patches, drafts customer replies, and opens a GitHub PR — with a human approval gate | LangGraph, Groq, ChromaDB, Streamlit, GitHub API | Repo |
| 🏥 Clinic Voice Agent | Real-time phone voice agent for clinic appointment booking built on raw Twilio Media Streams — no hosted platform, full STT → LangGraph → TTS pipeline | Twilio, Deepgram, ElevenLabs, LangGraph, FastAPI | Repo |
| 🔒 RAG RBAC Chatbot | Enterprise knowledge-base chatbot with namespace-scoped retrieval, JWT auth, hybrid BM25 + vector search, PII redaction, and Llama Guard safety — RAGAS faithfulness 0.91 | LangChain, ChromaDB, FastAPI, Redis, Streamlit | Repo |
| 🧬 Non-Linear Code Refactoring | Formal study proving Discrete Latent Diffusion Models (LLaDA 1.5 + Path-Guided Unmasking) outperform autoregressive models on complex cross-file refactoring tasks | LLaDA 1.5, PyTorch, Transformers | Repo |
I'm always open to interesting conversations, collaboration, or just a friendly chat.
📫 Reach me at aditya.rallapalli0902@gmail.com or connect on LinkedIn.
