Research Engineer (Agentic Models) (m/f/d)
Core
Design, implement, and maintain SFT and RL post-training pipelines for multi-step coding agents that understand codebases, plan changes, and call tools within JetBrains IDEs.
Role type
Senior IC research engineer (agentic models)
Builds
Multi-step coding agents, training loops, evaluation pipelines, and production models for JetBrains IDEs
Domain
Developer tools / AI agents / Large Language Models
Deliverable
production ML models
Required skills
LLM post-training (SFT/RL), PyTorch, distributed GPU training, data pipeline design, evaluation framework design, Python
Preferred skills
ML orchestrators (Kubeflow/Dagster/Airflow), large-scale data processing (MapReduce), experiment tracking (W&B/MLflow), inference optimization, agentic frameworks
Technologies
PyTorch, Megatron, NeMo, verl, Kubernetes, SLURM, Weights & Biases, MLflow, Langfuse
Responsibilities
Design and maintain SFT and RL post-training pipelines; Train and adapt LLMs for agent workflows; Build evaluation and simulation environments; Analyze training results to improve model architectures and datasets; Collaborate with product and infrastructure teams to ship features
Seniority
Senior, hands-on IC
