Note: The job is a remote job and is open to candidates in USA. Dynamo AI is building the future of trustworthy AI for the enterprise. This role involves defining and neutralizing security risks in agentic systems through research-heavy and engineering-heavy responsibilities, including designing experiments and building prototypes.
Responsibilities
- Define and validate threat models for agentic systems, identifying which tool characteristics must co-exist to enable data exfiltration and malicious state change, and how to break those combinations
- Design and run experiments: create synthetic environments like file systems and tools, create task distributions that have attack paths and apply different attack strategies
- Break (manually and using optimization algorithms such as RL) agentic systems in
- Design and improve static and dynamic analysis methods that automatically map tool capabilities to risk across diverse tool ecosystems, and make those methods scale
- Turn research insights into product-facing capabilities: risk classification, automated guardrail generation, and quantitative threat measurement
- Build measurement tools: eval harnesses, monitoring, dashboards, and feedback loops that quantify security outcomes
- Build capability and regression evals
- Optimize systems for real-world constraints (latency, cost, reliability) without losing scientific rigor
Skills
- MS or PhD in CS/ML (or equivalent research experience)
- Experience fine-tuning and evaluating models in practice
- Ability to reason about data quality, overfitting, evals, and deployment constraints
- Strong production code writing skills
- Comfortable owning the infrastructure that makes agentic evals run end-to-end
- Care about reproducibility and instrumentation
- Motivated by security problems and enjoy thinking like both builder and attacker
- Ability to reason about how capabilities combine into risk
- Clear communication skills
- Ability to iterate fast
- Ability to hold a technical narrative from 'hypothesis' to 'shipped'
Benefits
- Competitive salary + equity, so you share in the company's upside
- Work at the forefront of AI security, helping define a new category
- Remote-friendly, with a preference for candidates based in Amsterdam, Paris, Poland, New York, or San Francisco
- Fully funded team retreats every 8 weeks
- Health insurance allowance for you and your dependents
- Wellbeing, learning, and home office allowances (to support health, growth, and your setup)
Company Overview
Company H1B Sponsorship