Shaswat Singh

I’m an AI Engineering Intern focused on building production-ready LLM systems, real-time AI pipelines, and explainable ML solutions. I designed and deployed AI agents and scalable pipelines integrated into existing products via APIs, emphasizing seamless production adoption, low-latency inference, and robust backend architecture.

I build end-to-end applications that turn research into deployment—like PrepAI, an intelligent interview and notes assistant using conversational AI, RAG, and voice synthesis for real-time mock interviews. I also develop real-time computer vision with Guardian-Eye.AI (YOLOv8 on live CCTV feeds, under 2 seconds alert latency) and automate developer content generation with DevEcho (80% less content creation time), while advancing explainability through frameworks like AccidentGPT using TreeSHAP.