Strong understanding of transformer architectures and language modeling objectives.
Proficient in Python and PyTorch, with experience in Hugging Face tools.
Demonstrated ability in supervised fine-tuning and hyperparameter tuning.
Experience with parameter-efficient fine-tuning methods like LoRA or QLoRA.
Skilled in building instruction-response datasets and managing data integrity.
Familiar with multi-GPU training and frameworks like PyTorch FSDP or DeepSpeed.
Ability to design benchmarks and troubleshoot model performance issues.
Experience in experiment tracking and reproducible training practices.
Responsibilities
Lead design and execution of LLM training and fine-tuning projects.
Oversee preparation of high-quality training datasets.
Develop and optimize fine-tuning workflows and apply preference optimization methods.
Establish evaluation frameworks for model performance and safety.
Diagnose training issues to enhance model quality and efficiency.
Manage and mentor data scientists, ensuring reproducible practices.
Collaborate with cross-functional teams to define requirements and support model deployment.
Manage project priorities, timelines, and communicate results to stakeholders.
Benefits
Promotes a healthy work/life balance with flexible working hours.
Offers wellbeing initiatives and shared parental leave.
Provides study assistance and sabbaticals for personal growth.
Country-specific benefits tailored to employee needs.
Full Job Description
Responsibilities
Lead the design and execution of LLM training and fine-tuning projects, including model selection, training strategy, experimentation, and evaluation.
Oversee the preparation of high-quality training datasets, including data collection, cleaning, deduplication, annotation, and quality validation.
Develop and optimize supervised fine-tuning and parameter-efficient fine-tuning workflows; apply preference optimization methods where appropriate.
Establish evaluation frameworks to assess factual accuracy, instruction following, domain relevance, safety, and performance on business-specific tasks.
Diagnose training issues and improve model quality, training stability, GPU utilization, and computational efficiency.
Manage and mentor data scientists, review technical work, and establish reproducible development practices.
Partner with product, engineering, and domain experts to define requirements and support model deployment and monitoring.
Manage project priorities, timelines, and compute resources, and communicate results and tradeoffs to stakeholders.
Required technical skills
LLM fundamentals: Strong understanding of transformer architectures, attention mechanisms, tokenization, language modeling objectives, and the differences between pretraining, continued pretraining, and fine-tuning.
Programming and frameworks: Strong Python and PyTorch skills, with practical experience using Hugging Face Transformers, Datasets, or equivalent tools.
Hands-on LLM training: Demonstrated ability to implement supervised fine-tuning (SFT), configure training objectives and loss masking, tune hyperparameters, and select model checkpoints.
Efficient fine-tuning: Practical experience with parameter-efficient fine-tuning (PEFT), including LoRA or QLoRA, and an understanding of their quality, memory, and compute tradeoffs.
Training data engineering: Ability to build instruction-response datasets, apply chat templates, manage sequence lengths and packing, and prevent data leakage and evaluation contamination.
GPU and distributed training: Experience training models across multiple GPUs using frameworks such as PyTorch FSDP or DeepSpeed, including mixed precision, gradient accumulation, and gradient checkpointing.
Evaluation and debugging: Ability to design reliable benchmarks and human evaluations, analyze model errors, and troubleshoot unstable loss, overfitting, and GPU memory issues.
Reproducibility: Experience with experiment tracking, dataset and model versioning, checkpoint management, and documented training pipelines.
Work in a Way That Works for You
We promote a healthy work/life balance across the organisation. We offer an appealing working prospect for our people. With numerous wellbeing initiatives, shared parental leave, study assistance and sabbaticals, we will help you meet your immediate responsibilities and your long-term goals.
Working Pattern
Working flexible hours - flexing the times when you work in the day to help you fit everything in and work when you are the most productive.
U.S. National Base Pay Range: $115,400 - $192,300. Geographic differentials may apply in some locations to better reflect local market rates.This job is eligible for an annual incentive bonus. We know your well-being and happiness are key to a long and successful career. We are delighted to offer country specific benefits. Click here to access benefits specific to your location.
About Relx Group
RELX Group is a global provider of information-based analytics and decision tools for professional and business customers. The company operates in four market segments: scientific, technical and medical; risk and business analytics; legal; and exhibitions. RELX's products and services include electronic databases, online information services, workflow tools, and print and digital books. The company was founded in 1993 and is headquartered in London, England.
