I’m an AI/ML and Backend engineer focused on building production-grade GenAI systems—especially RAG pipelines, multi-agent architectures, and low-latency LLM inference. I’ve worked across the stack to ship real features for users, with a strong emphasis on measurable performance (latency, throughput, and cost) and reliable experimentation. I’m comfortable taking models from research to deployment, including quantization and inference optimization, and then wrapping them with robust APIs, telemetry, and dashboards. I enjoy engineering systems that go beyond demos—routing requests intelligently, tracking quality and drift, and continuously improving evaluation results to deliver dependable AI-powered products.…I’m an AI/ML and Backend engineer focused on building production-grade GenAI systems—especially RAG pipelines, multi-agent architectures, and low-latency LLM inference. I’ve worked across the stack to ship real features for users, with a strong emphasis on measurable performance (latency, throughput, and cost) and reliable experimentation. I’m comfortable taking models from research to deployment, including quantization and inference optimization, and then wrapping them with robust APIs, telemetry, and dashboards. I enjoy engineering systems that go beyond demos—routing requests intelligently, tracking quality and drift, and continuously improving evaluation results to deliver dependable AI-powered products.WWWW…