Responsibilities
- Develop and sustain the AI reasoning component and agent orchestration system that form the foundation of the Compliance in a Box platform
- Create and deploy a system composed of seven specialized AI agents: OnboardingAgent, ScopeAgent, StandardsMapper, RiskQuantifier, PolicyAnalyzer, InfrastructureAuditor, and ComplianceMonitor
- Integrate human review checkpoints into agent workflows and refine prompts and confidence metrics for models hosted on Bedrock
- Lead the evaluation framework for AI agents, ensuring performance, speed, and dependability meet production standards
- Work closely with multidisciplinary teams to ensure full feature delivery of Compliance in a Box by Week 7, with rapid deployment cycles and immediate impact
Requirements
- Bachelor’s or higher degree in Computer Science, Software Engineering, or a related IT field
- Proven knowledge of artificial intelligence and machine learning principles, particularly large language models and agent-based architectures
- Proficiency in writing clear, maintainable, and thoroughly tested code, with a preference for Python
- Track record of delivering production-grade AI systems, beyond simple conversational interfaces
- Excellent communication abilities and a team-oriented approach
Nice to Have
- Experience with AWS technologies, particularly Amazon Bedrock or comparable LLM deployment platforms
- Understanding of governance, risk, and compliance (GRC) principles or cybersecurity standards like ISO 27001 or SOC 2
- Hands-on experience with agent orchestration tools such as LangChain, CrewAI, or AutoGen
