onsite
Applied Scientist, AI Risk - Armilla Ai
Software Engineer
Lead research on AI risk mitigation, developing advanced ML models to detect and counteract harmful AI behaviors using Python, PyTorch, and NLP techniques.
About the role
Key Responsibilities
- Design and implement machine learning pipelines to identify and mitigate AI safety risks across large-scale models.
- Develop NLP-based detection systems for bias, toxicity, and adversarial manipulation in text and multimodal outputs.
- Collaborate with cross-functional teams to integrate risk assessment modules into production AI services.
- Conduct rigorous statistical analysis and ablation studies to validate model robustness and fairness.
- Publish findings in internal reports and external conferences, contributing to the broader AI safety community.
Requirements
- PhD or MS in Computer Science, Machine Learning, or related field with focus on AI safety or NLP.
- Proven experience building deep learning models using PyTorch or TensorFlow.
- Strong programming skills in Python and familiarity with data engineering tools.
- Excellent analytical skills, with a track record of publishing research on AI risk or related topics.
- Effective communicator capable of translating complex technical concepts to non‑technical stakeholders.
Skills
machine learningnatural language processingdeep learningpythonpytorch