Principal, AI Engineer

Principal, AI Engineer

Salary: Open + Bonus

Location: Chicago, IL

Hybrid: 3 days onsite, 2 days remote

*We are unable to provide sponsorship for this role*

Qualifications

• Bachelor's degree
• 10+ years of software engineering and systems architecture experience, with demonstrated technical leadership
• 5+ years as a senior individual contributor on complex, high-stakes production systems
• Expert-level Python; proficient in SQL
• Deep system design expertise: distributed systems, microservices, event-driven architectures, APIs, and MCP servers
• Hands-on experience with data engineering: pipelines, transformation, and data modeling
• AWS experience; comfort with Docker, Kubernetes, and CI/CD pipelines
• Strong production AI/LLM experience
• Strong working knowledge of AI risk vectors: hallucinations, prompt injection, bias, data privacy, and output validation
• Familiarity with frontier models including Claude, GPT, and Gemini, and hands-on experimentation with emerging tools
• Experience connecting AI agents to enterprise systems and workflows
• Infrastructure as code (Terraform)

Preferred

• Production experience building and operating LLM-powered applications
• Experience designing and operating agentic AI systems in enterprise environments
• Hands-on experience with Anthropic s tooling and APIs, including the Claude API, Claude.ai, or the Anthropic Console

Responsibilities

• Partner with the Executive Director of AI Engineering to define and execute AI technical roadmap, translating organizational priorities into concrete architectural decisions
• Lead agentic AI efforts: architect, build, and operate systems that connect AI agents to internal systems, data pipelines, and business workflows
• Leverage direct relationships with AWS and Anthropic to evaluate and adopt new model capabilities and tooling as they become available
• Build and ship production AI applications on AWS using Claude and related Anthropic tooling, maintaining high standards for reliability, security, and auditability
• Architect scalable systems that integrate LLMs and AI agents into internal systems, operational workflows, and business processes, owning decisions from design through production deployment
• Serve as the primary technical mentor for junior engineers: conducting code and architecture reviews, modeling engineering best practices, and raising the team's overall technical level (no direct reports)
• Define and enforce AI safety standards appropriate for a regulated SIFMU environment, including hallucination detection, output validation, bias assessment, and audit trails that satisfy SEC and CFTC oversight expectations
• Establish responsible AI practices and safety guardrails for LLM applications operating on sensitive financial data
• Navigate change management and security review processes when deploying AI systems into production
• Evaluate emerging AI technologies and provide concrete, risk-aware recommendations on adoption