Responsibilities
- Own an ML privacy vertical e.g. data leakage attacks, sensitive PII detection, and/or membership inference attacks.
- Collaborate with our engineering team to deliver real-world applications of your algorithms for our customers.
- Generate high quality synthetic training data, train LLMs, and conduct rigorous evaluation and benchmarking.
Qualifications
- Deep domain knowledge in privacy-preserving ML.
- Practical experience in techniques to attack or defend ML models in terms of privacy.
- Extensive experience in implementing multiple different types of LLM models and architectures in the real world. Comfortability with leading end-to-end projects.
- Adaptability and flexibility. In both the academic and startup world, a new finding in the community may necessitate an abrupt shift in focus. You must be able to learn, implement, and extend state-of-the-art research.
- Preferred: previous projects or research in LLM privacy.
Top Skills
What We Do
Dynamo AI is pioneering the first end-to-end secure and compliant generative AI infrastructure that runs in any on-premise or cloud environment.
With a holistic approach to GenAI compliance, we help accelerate enterprise adoption to deploy secure, reliable, and compliant AI applications at scale.
Our platform includes three products:
- DynamoEval evaluates GenAI models for security, hallucination, privacy, and compliance risks.
- DynamoEnhance remediates identified risks, ensuring more reliable operations.
- DynamoGuard offers real-time guardrailing, customizable in natural language and with minimal latency
Our client base and partnerships include Fortune 1000 companies across all industries, which underscores our proven success in securing GenAI in highly regulated environments
