Intelligence Architect
Designs and authors context, procedures, skills, and system prompts for AI agents performing autonomous accounting tasks. Ensures consistency, monitors performance, and shapes future capabilities through precise language and systems thinking.
About the job
Responsibilities
- Architect and author agents' context, including procedures, skills, and system prompts.
- Set standards for consistency across agents, defining how procedures and skills are written.
- Monitor agent performance, identify context gaps, and improve outputs.
- Shape future product decisions based on agent capabilities and improvements.
Requirements
- Excellent writing skills, treating language as load-bearing with precise prose.
- Strong systems reasoning and ability to understand root causes.
- Comfort in ambiguity and frontier problems without textbook answers.
- Quick learning to build accurate mental models of new domains like accounting.
- Ability to hold multiple factors (user problems, agent behavior, procedures, success measures) simultaneously.
Nice-to-Haves
- Background in engineering, product management, philosophy, law, accounting, editing, or academia with curiosity about AI agents.
Skills
System Prompts, AI Agents, Procedures, Skills Authoring, Evaluations, Context Engineering, Reasoning Systems, Domain Knowledge, Prompt Engineering, Agent Architecture
Similar jobs
AI Research jobs
AI Digest
Remote
Conduct research on long-horizon, multi-agent AI behavior by designing agent environments, analyzing large-scale data, and running experiments. The role requires strong research judgment, rapid execution, independence, and familiarity with current AI developments.
AI Digest
Remote
Build, optimize, and evaluate long-running and multi-agent AI systems, along with tools for monitoring and analyzing their real-world behavior. The role requires software engineering experience with coding agents, strong independence, and familiarity with current AI developments.
Counsel Health
New York, NYResearch Scientist developing and evaluating health-focused AI models, large language models, and agentic systems for clinical applications. The role requires advanced research experience, strong coding skills, healthcare or clinical-data experience, and top-tier AI/ML publications.
Mercor
San Francisco, CA
Research Engineer focused on designing benchmarks, evaluation systems, rubrics, and failure-analysis workflows for frontier language models. The role requires strong applied AI research and coding experience, with expertise in model evaluation, data quality, and backend systems.
Hightouch
United States
Develops experimental AI techniques and prototypes for agentic marketing applications, with emphasis on image and video generation. The role requires strong backend or probabilistic systems expertise, quantitative thinking, creativity with LLM applications, and product intuition.