IT Developer - LLM Engineer

Careers that change lives start here. Medtronic is a global leader in healthcare technology with a Mission to alleviate pain, restore health, and extend life. Our 95,000 employees work across more than 150 countries to put patients first — developing innovative medical technologies that improve the lives of 72+ million patients each year. Your unique talents will help shape the future of healthcare while building a career grounded in purpose, growth, and impact. A Day in the Life As an IT Developer focused on Applied AI and Large Language Model engineering, you will design, evaluate, optimize, and operationalize enterprise AI systems across the complete model lifecycle. You will partner with platform engineers, data engineers, security teams, and domain experts to improve model quality, deploy production-ready AI solutions, establish evaluation frameworks, and drive measurable outcomes through data-driven experimentation and governance. Responsibilities may include the following and other duties may be assigned. Design and implement training, fine-tuning, and adaptation pipelines for open-weight Large Language Models using supervised fine-tuning, LoRA, QLoRA, and Parameter-Efficient Fine-Tuning (PEFT) techniques. Build and curate high-quality datasets from operational data sources, incidents, runbooks, logs, knowledge articles, and validated interactions for model training and evaluation. Develop model evaluation frameworks covering reasoning, instruction following, hallucination detection, tool calling, safety, robustness, and structured output quality. Evaluate and optimize retrieval-augmented generation systems through retrieval analysis, embedding model comparison, reranking, chunking strategies, and groundedness assessment. Design and execute agent and tool-calling benchmarks that measure task completion, tool selection accuracy, failure recovery, and operational safety. Optimize model serving performance through quantization, batching strategies, cache management, inference tuning, and serving-stack evaluation. Implement experiment tracking, model governance, lineage management, release gating, and deployment workflows using enterprise MLOps practices. Establish production monitoring, quality drift detection, observability metrics, security testing, and rollback criteria for deployed AI solutions. Required Knowledge and Experience:  3+ years of IT experience with a Bachelor's Degree in Engineering, MCA, or MSc. with 3+ years of software engineering or machine learning experience, including 2+ years of hands-on Generative AI or Large Language Model development. Experience with Python, PyTorch, Hugging Face Transformers, Datasets, PEFT, and model fine-tuning workflows. Experience implementing Large Language Model evaluation, retrieval-augmented generation, model benchmarking, and experiment tracking frameworks. Experience with Linux, Docker, Kubernetes, Git, REST APIs, and cloud or GPU-based model deployment environments.