LLM Fine-Tuning Engineer

Design, execute, and operationalize fine-tuning workflows for large language models across supervised, preference-based, and reinforcement learning approaches. Lead dataset construction, curation, and quality assurance for instruction tuning and preference data. Build scalable training pipelines on top of modern distributed training frameworks. Tune hyperparameters and training stability strategies for large-model fine-tuning. Implement parameter-efficient fine-tuning techniques such as LoRA, QLoRA, and adapter-based methods. Design rigorous evaluation suites including automated benchmarks and human evaluation. Implement safety, refusal, and policy evaluations to track model behavior across releases. Operate large-scale training jobs on GPU clusters, diagnose failures, and recover training state reliably. Optimize training throughput with mixed precision and efficient attention implementations. Manage model artifacts, lineage tracking, and reproducibility across experiments. Collaborate with product, research, and platform teams to align roadmaps with business needs. Document training methodology and results for technical and non-technical audiences. Mentor engineers on best practices, and stay current with LLM research to translate advances into production-ready fine-tuning recipes.