Research Engineer
Gauntlet provides institutional-grade vault curation and risk management services for DeFi protocols through quantitative optimization and simulation modeling.
Funding history
Projects
About Gauntlet
Gauntlet offers risk-adjusted DeFi yields through curated vault strategies and applied research services for blockchain protocols. The platform utilizes agent-based simulations, quantitative modeling, and real-time monitoring to optimize protocol parameters, manage market risk, and curate lending, restaking, and perpetual futures vaults across multiple blockchains. Gauntlet's infrastructure processes over 400 million data points daily to inform risk management decisions for protocols securing billions in total value locked.
Skills
About the Role
You'll help improve how AI agents are built, evaluated and used across the business. You'll build evaluation frameworks that measure agent performance on real tasks, design experiments, investigate agent failures, and contribute directly to existing agents like Aria and internal tooling. Initially the work is more engineering-focused, and over time you'll take on more open-ended research on evaluation, agent behaviour and infrastructure, including shared knowledge and reusable skills for agents.
Requirements
- Hands-on experience building, evaluating or improving LLM models or agents
- Strong Python skills and good software engineering fundamentals
- Experience with applied research, machine learning or data science, including designing experiments
- Understanding of how LLM agents work, including tool use, harnesses, context management and failure modes
- Ability to break down open-ended problems into testable questions and work independently
- Experience building tools or systems that other people use
- Comfort working across research and engineering and collaborating with different teams
- Genuine interest in AI agents
Responsibilities
- Build evaluation frameworks for AI agents, including datasets, sandbox environments and metrics
- Design experiments to compare models, agent harnesses, tools and execution environments
- Turn qualitative feedback about agent behaviour into research questions, experiments and measurable outcomes
- Investigate agent failures and determine whether they come from the model, harness, tooling or prompting
- Build and improve agent harnesses, internal tools and integrations, including Aria
- Develop shared knowledge and reusable skills across agents
- Work with Infrastructure and Security to ensure agents operate reliably and safely in production
Benefits
- Remote first — work from anywhere in the United States
- Regular in-person company retreats and cross-country office visit perk
- 100% paid medical, dental, and vision premiums for employees
- $1,000 WFH stipend
- Monthly reimbursement for home internet, phone, and cellular data
- Unlimited vacation
- 100% paid parental leave of 12 weeks
- Fertility benefits
- Opportunity for incentive compensation
- Equity in the company