Note: The job is a remote job and is open to candidates in USA. Sustainable Talent is partnering with Nvidia, a global leader in computer graphics and accelerated computing. They are seeking an AI Security Engineer to support the team in Santa Clara, CA, focusing on AI Safety for LLMs and collaborating with research and engineering teams to enhance the safety and inclusivity of LLM models.
Responsibilities
- Develop datasets and moderator models for evaluating LLM models and end-to-end systems for Content Safety, ML Fairness. These LLM models can be txt-to-txt or multimodal-to-txt
- Develop datasets for training LLM models with SFT and RL techniques, for Content Safety, ML Fairness, Security and more
- Research and implement cutting-edge techniques for bias detection and mitigation in LLMs and systems
- Define and track key metrics for responsible LLM behavior and usage
- Follow the best practices of automation, monitoring, scale, safety
- Contribute to our repositories and develop safety tools to help ML teams be more effective
- Data pre-processing and analysis: Collaborate with data scientists and data engineers to collect, clean, pre-process, and transform large and wide datasets
- Conduct exploratory data analysis (EDA) to uncover insights and identify patterns that boost the model performance
- Collaborate with multidisciplinary teams: Collaborate with product engineers, data scientists, and analysts to understand business requirements and translate them into machine learning solutions
Skills
- Bachelor's or Master's Degree in Computer Science or related field or equivalent experience
- 2+ years of work experience as a Machine Learning Engineer or Deep Learning Scientist or a similar role, with a consistent record of successfully delivering ML solutions
- Strong programming skills in languages such as Python. Experience with frameworks like TensorFlow, PyTorch, or scikit-learn
- Proficiency in data manipulation, analysis, and visualization using tools like NumPy and pandas
- Deep understanding of machine learning algorithms, statistical models, and data structures
- Familiarity with software development practices and version control systems (e.g., Git)
- Good at problem solving and analytical ability
- Excellent collaboration and communication skills
- Experience with GenAI Security including Prompt Injection Stability, Model Extraction, Confidentiality/Data Extraction, Integrity, Availability and Adversarial Robustness
- Experience with one or more of the following areas within Content Safety: Hate/Harassment, Sexualized, Harmful/Violent, or other specific areas from your application
- Experience with alignment/fine-tuning of LLMs - including regular LLMs as well as VLMs (Vision Language Model) or any-to-text
- Experience with multimodal and/or multilingual Content Safety, legal and regulatory compliance
- Passion for AI and a demonstrated commitment to advancing the field through innovative research, prior scientific research and publication experience
Benefits
- Full benefits
- PTO
- Amazing company culture
- Remote/ hybrid work options
Company Overview