Research Engineer
Core
Build evaluation frameworks, datasets, and metrics to measure AI agent performance on real-world tasks; design experiments to improve agent reliability and infrastructure.
Role type
Senior IC AI Research Engineer (Agents & Evaluation)
Builds
Evaluation frameworks, agent harnesses, internal tools, and shared knowledge systems for AI agents.
Domain
AI Agents, Machine Learning, Quantitative Research, DeFi/Financial Systems
Deliverable
production ML models
Required skills
LLM agent development, Python, software engineering, experimental design, data analysis, tool use, context management, failure mode analysis
Preferred skills
LLM evaluation pipelines, reinforcement learning, open-source agent frameworks, financial markets/DeFi experience, AI security
Technologies
Python, LLMs, agent harnesses, evaluation datasets
Responsibilities
Build evaluation frameworks and metrics for AI agents; design experiments to compare models and tools; investigate agent failures and develop improvements; build and maintain agent harnesses and internal tools; collaborate with infrastructure and security teams.
Seniority
Senior, hands-on IC