AI Benchmarking & Evaluation Engineer

Join a team at the forefront of AI model evaluation, setting the standard for how large language models are tested and validated. In this role, you'll assess the latest AI models, design new benchmarks, and develop advanced evaluation methodologies. You'll work closely with engineers, AI researchers, and enterprise clients to ensure cutting-edge AI systems meet the highest standards. This role is a bridge between research and practical implementation and will suit someone who enjoys taking academic papers and creating working models.

Key Responsibilities:

• Analyze and benchmark newly released AI models (DeepSeek, Gemini, etc.)
• Develop and implement novel evaluation frameworks
• Build datasets, manage labeling processes, and publish findings
• Enhance automated evaluation techniques for AI-generated content
• Collaborate with top AI labs and enterprise partners to refine best practices

Who You Are:

• MSc or PhD from leading Computer Science or Machine Learning school
• At least 3 years of experience in applied AI, with a focus on benchmarking or model evaluation
• Strong background in designing evaluation methodologies
• Passion for advancing AI assessment standards
• Solid Python, PyTorch/TensorFlow and Django

Make a real impact in AI research and development—apply today!