Hi, I'm Bhavana Kendhyala, an AI/ML Engineer with 4+ years of hands-on experience building LLM-based systems, agentic AI workflows, multimodal apps, and retrieval-augmented generation pipelines on GPU-accelerated infrastructure. I have deep hands-on experience with transformer models like LLaMA and BERT, fine-tuning with LoRA and SFT, and optimizing distributed inference with vLLM to serve models at scale. I've designed end-to-end ML systems spanning data pipelines, training workflows, evaluation frameworks, and production deployment with a focus on latency, scalability, and retrieval quality. My work blends research with practical deployment, collaborating across engineering teams to deliver robust AI solutions.…Hi, I'm Bhavana Kendhyala, an AI/ML Engineer with 4+ years of hands-on experience building LLM-based systems, agentic AI workflows, multimodal apps, and retrieval-augmented generation pipelines on GPU-accelerated infrastructure. I have deep hands-on experience with transformer models like LLaMA and BERT, fine-tuning with LoRA and SFT, and optimizing distributed inference with vLLM to serve models at scale. I've designed end-to-end ML systems spanning data pipelines, training workflows, evaluation frameworks, and production deployment with a focus on latency, scalability, and retrieval quality. My work blends research with practical deployment, collaborating across engineering teams to deliver robust AI solutions.WWWW…