AI Verification Research Scientist: ML Evaluation Benchmarks

Meta; Paris; Hybride; EUR 90 000 - 130 000; Plein temps

Résumé du poste

Meta is seeking Research Scientists to join our AI Verification team. You will work on model training, evaluation benchmarks, and trustworthy AI, bridging symbolic verification with neural AI.

Qualifications include a PhD in CS/AI/ML, publications at top AI conferences, experience with large-scale training infra and data pipelines, and ability to design robust evaluation benchmarks. You will need work authorization in France.

Qualifications

• PhD in Computer Science, AI, ML, or related field.
• Experience in ML model evaluation, training pipelines, or benchmark and agent design and evaluation.
• Publications in ML/AI or related fields.
• Author publications at peer-reviewed AI conferences (e.g. NeurIPS, ICML, ICLR, ACL, EMNLP).
• Experience with large-scale training infrastructure and data pipelines.
• Experience designing evaluation benchmarks for large AI models or agents.
• Familiarity with formal verification or automatic program analysis.

Responsabilités

• Join the AI Verification team to advance trustworthy AI models.
• Design and evaluate data and environments to train ML models and benchmarks.
• Develop evaluation benchmarks for agents and models.
• Connect symbolic verification with neural AI.

Connaissances

ML model evaluation

Publications in ML/AI

Large-scale training infra

Evaluation benchmarks design

Formal verification / program analysis

Formation

PhD in Computer Science / AI / ML

Description du poste

Meta is seeking Research Scientists to join our AI Verification team. You will work on model training, evaluation benchmarks, and trustworthy AI, bridging symbolic verification with neural AI.

Qualifications include a PhD in CS/AI/ML, publications at top AI conferences, experience with large-scale training infra and data pipelines, and ability to design robust evaluation benchmarks. You will need work authorization in France.