Siddh User

I build and deploy AI systems across internships, research projects, and production implementations, with over two years of hands-on experience in Python, LLMs, RAG pipelines, agentic AI, vector search, and cloud-native APIs. I emphasize reliable MLOps practices—model versioning, containerization, CI/CD, and production reliability—while optimizing inference cost, latency, and throughput.

My work includes production-grade generative pipelines for animated media, scalable FastAPI ML services with containerized deployments and CI/CD, and high-accuracy ML systems such as workforce punctuality prediction and an LLM-driven gaming bot detector. I focus on pragmatic engineering, prompt and API orchestration, and measurable improvements in retrieval relevance and operational efficiency.