onsite
Research Engineer - Large Language Models for Multi Agent Systems
Research Engineer
Research Engineer focused on developing and evaluating large language models for multi‑agent AI systems, leveraging Python, PyTorch, Azure cloud services, and CI/CD pipelines to advance autonomous, agentic AI capabilities.
About the role
Key Responsibilities
- Design, implement, and fine‑tune large language models (LLMs) tailored for multi‑agent coordination and decision‑making.
- Develop simulation environments and evaluation frameworks to benchmark agentic AI performance.
- Integrate LLMs with Azure cloud services, ensuring scalable deployment and efficient resource utilization.
- Build and maintain CI/CD pipelines for automated testing, model versioning, and continuous delivery.
- Collaborate with cross‑functional research teams to publish findings and translate research prototypes into production‑ready components.
Requirements
- Strong programming skills in Python and experience with deep‑learning frameworks such as PyTorch.
- Hands‑on experience with large language models (e.g., GPT, LLaMA) and prompt engineering for multi‑agent contexts.
- Proficiency in Azure cloud services and modern CI/CD tools (e.g., GitHub Actions, Azure Pipelines).
- Background in multi‑agent systems, reinforcement learning, or related AI research areas.
- Ability to work independently, publish research results, and communicate complex concepts clearly.
Skills
pythonpytorchazurecicd