Research Engineer (Agentic Models)

Stack

Responsibilities

• ▹Design, implement and maintain SFT and RL post-training pipelines for multi-step coding agents
• ▹Train and adapt LLMs for agent workflows, including planning, tool use and multi-step interactions inside JetBrains IDEs
• ▹Build evaluation and simulation environments where coding agents can act and be measured and compared on realistic developer tasks
• ▹Design evaluation frameworks and metrics for agent behavior, analyze traces and logs, and close the loop back into training, data and reward design
• ▹Analyze training and evaluation results and propose improvements to model architectures, training recipes and datasets
• ▹Work with large-scale infrastructure, including distributed training on GPU clusters and MapReduce-style data processing
• ▹Collaborate closely with research, product and infrastructure teams

Requirements

• ▹Extensive hands-on experience training LLMs (pre-training, fine-tuning or post-training) in a research or production setting
• ▹Deep expertise in deep learning frameworks such as PyTorch and LLM training stacks (e.g. Megatron, NeMo, verl)
• ▹Strong understanding of LLM fundamentals: architectures, tokenization, data pipelines, batching, mixed precision, distributed training and debugging unstable runs
• ▹Ability to own projects end to end, from a high-level problem through design, experimentation, implementation and iteration
• ▹A product-aware mindset: understanding how developers use agents and translating product needs into modeling and evaluation work
• ▹At least 3 years of Python experience writing clean, maintainable code in modern ML codebases

Nice to have

• ▹ML orchestrators and workflow tools such as Kubeflow, Dagster, Airflow, ZenML, and job schedulers like Kubernetes or SLURM
• ▹Large-scale data and training pipelines, e.g. MapReduce-style clusters, multi-node GPU training, workloads of 1M+ CPU/GPU hours
• ▹Designing and maintaining evaluation pipelines for LLMs or agents, including metrics, dashboards, experiment tracking and automated regression checks
• ▹AI agent development: tool-using agents, planners, multi-step coding workflows, agentic frameworks
• ▹Experiment tracking and observability with tools like Weights & Biases, MLflow or Langfuse
• ▹Inference optimization and serving optimized models in production

Soft skills

About the company

JetBrains has been building developer tools since 2000. AI-powered assistance and agents are now a core part of how developers work in its IDEs.