Staff Research Engineer (LLM Pre-Training)

About the Position

At JetBrains, we are passionate about code. Since our inception in 2000, we have been dedicated to creating the most robust and effective developer tools. By automating routine checks and corrections, our tools accelerate production, allowing developers to grow, discover, and create.

We are currently working on an ambitious new platform that integrates AI capabilities into all JetBrains products. Our platform is built on models developed in-house for writing and coding assistance, as well as through partnerships with strategic entities.

We are seeking a Staff Research Engineer (LLM Pre-Training) to contribute to training foundation models for coding tasks. You will be responsible for developing Large Language Models from scratch and deploying them into production environments, making them accessible to end users worldwide.

Responsibilities

• Collaborate with stakeholders to translate business requirements into technical specifications.
• Train LLMs from scratch on a large GPU cluster.
• Collect and process pre-training and fine-tuning datasets.
• Support and improve existing subsystems.

Requirements

• Experience in the design, deployment, and support of production ML systems.
• A strong theoretical background in NLP and transformer-based approaches.
• Proficiency with modern deep learning frameworks such as PyTorch and common NLP libraries.
• Experience in distributed training of multi-billion parameter models.
• Attention to detail and excellent communication skills.

Nice to Have

• Experience with LLM inference frameworks such as vLLM, DeepSpeed, TensorRT.
• Knowledge of LLM alignment techniques such as RLHF/RLAIF.
• Familiarity with MLOps tools and practices, including CI/CD for ML.
• Experience with K8s and Kubeflow.
• Scientific publications in the NLP field.

We Offer

• A cluster of hundreds of NVIDIA GPUs as training infrastructure.
• Git for source control management.
• Python, PyTorch, and HuggingFace as the ML stack.
• Kubeflow and Weights & Biases for experiment tracking.
• TeamCity as a CI Automation system.

About the Company

We are an equal opportunity employer. We believe that great ideas can come from anyone, anywhere. That’s why we strive to create an open and inclusive workplace that welcomes everyone, regardless of their background, identity, religion, age, accessibility needs, or orientation.

We process the data provided in your job application in accordance with the Recruitment Privacy Policy.