The engineer will participate in the scientific validation of AI models by measuring their accuracy robustness and consistency. His role will be to:
- Design and execute AI model testing and evaluation protocols (LLM classification models NLP etc.)
- Analyze performance and identify biases or weaknesses
- Propose improvements through prompt engineering
- Collaborate with data scientists and developers to refine models and optimize their use in production
- Produce performance reports and recommendations for improvement
Qualifications :
Strong scientific background (applied mathematics statistics physics computer science or equivalent)
Good understanding of Machine Learning and Large Language Models (LLM)
Experience in evaluating AI models (accuracy precision recall F1-score confusion matrix etc.)
Knowledge of Prompt Engineering (writing and optimization of prompts for LLM)
Skills in Python and AI libraries (TensorFlow PyTorch scikit-learn etc.)
Ability to analyze and interpret complex results
Good written and oral communication in English (Fluent English mandatory)
Informations supplémentaires :
Looking forward to hearing from you !
Remote Work :
Yes
Employment Type :
Full-time
The engineer will participate in the scientific validation of AI models by measuring their accuracy robustness and consistency. His role will be to:Design and execute AI model testing and evaluation protocols (LLM classification models NLP etc.)Analyze performance and identify biases or weaknessesPr...
The engineer will participate in the scientific validation of AI models by measuring their accuracy robustness and consistency. His role will be to:
- Design and execute AI model testing and evaluation protocols (LLM classification models NLP etc.)
- Analyze performance and identify biases or weaknesses
- Propose improvements through prompt engineering
- Collaborate with data scientists and developers to refine models and optimize their use in production
- Produce performance reports and recommendations for improvement
Qualifications :
Strong scientific background (applied mathematics statistics physics computer science or equivalent)
Good understanding of Machine Learning and Large Language Models (LLM)
Experience in evaluating AI models (accuracy precision recall F1-score confusion matrix etc.)
Knowledge of Prompt Engineering (writing and optimization of prompts for LLM)
Skills in Python and AI libraries (TensorFlow PyTorch scikit-learn etc.)
Ability to analyze and interpret complex results
Good written and oral communication in English (Fluent English mandatory)
Informations supplémentaires :
Looking forward to hearing from you !
Remote Work :
Yes
Employment Type :
Full-time
View more
View less