Researcher (Simulations)
Amigo
Posted on May 13, 2025
Researcher (Simulations)
To apply, send us your resume and anything else you'd like to careers@amigo.ai
About Amigo
We're helping enterprises build autonomous agents that reliably deliver specialized, complex services—healthcare, legal, and education—with practical precision and human-like judgment. Our mission is to build safe, reliable AI agents that organizations can genuinely depend on. We believe superhuman level agents will become an integral part of our economy over the next decade, and we've developed our own agent architecture to solve the fundamental trust problem in AI. Learn more here.
Role
As a Researcher in Simulation at Amigo, you'll advance our evolutionary chamber approach by developing sophisticated problem space simulation capabilities. Working as part of our Research team, you'll create techniques that accurately model complex domains and generate the evolutionary pressure necessary for agent improvement. You'll collaborate with domain expert partners to translate their expertise into effective simulator frameworks that can intelligently challenge agents across thousands of scenarios. This role is crucial for establishing the foundation of our continuous alignment loop and enabling agents to evolve toward superhuman performance.
Responsibilities
Design and develop advanced problem space simulation architectures that create precise evolutionary pressures for agent improvement
Create simulator models that use significantly more computational resources (reasoning tokens) to fully explore problem spaces beyond what the primary agent can achieve
Implement techniques for intelligent challenge generation that pushes system boundaries and uncovers edge cases
Build frameworks that enable domain-specific intelligence to be embedded in simulators
Develop methods for transparent reasoning in simulators that provide clear audit trails for every decision
Research approaches for simulator persona creation that can realistically model diverse user behaviors and interactions
Collaborate with domain experts to translate their knowledge into effective simulation environments
Design and implement methods for efficiently scaling simulations across thousands of scenarios while maintaining quality
Work with the Verification team to ensure simulators integrate effectively with judge systems
Contribute to research publications and the broader field of AI simulation and evaluation
Qualifications
PhD or equivalent research experience in AI, machine learning, reinforcement learning, or related fields
Strong understanding of LLM capabilities and limitations, particularly related to reasoning and simulation
Experience designing simulation environments or synthetic data generation systems
Background in designing systems that can model complex human behaviors or domain expertise
Familiarity with adversarial testing techniques and methods for uncovering edge cases
Strong programming skills with the ability to implement complex simulation frameworks
Understanding of evaluation metrics and how they interact with simulation environments
Excellent research and analytical skills with the ability to design and run rigorous experiments
Strong communication skills for collaborating with domain experts and cross-functional teams
Passion for building trustworthy AI that can be deployed responsibly in high-stakes domains
Location: NYC (Onsite)
To apply, send us your resume and anything else you'd like to careers@amigo.ai