AI Research and Engineering - Data Enigneering

• Data engineering (currently highest preference): ETL/ELT, data pipelines - needs to build a “knowledge substrate” to make corporate data (ServiceNow, JIRA, SaaS apps) consumable by AI models
• Software/application engineering: building agentic workflows
• Infrastructure: AWS infrastructure-as-code, containerization, deployment pipelines, * Own the design and delivery of agentic AI systems end-to-end, from architecture through production deployment
• Architect agent orchestration patterns, tool and context integration, and evaluation pipelines for reliability in a regulated environment
• Own AI infrastructure supporting AIRE’s agents and applications on AWS, and contribute to the team’s growing infrastructure self-sufficiency

• AI interest required, but deep experience is not - generative AI has only existed a few years; even 1-2 years of experience or strong interest is acceptable
• Strong soft skills and communication are a priority over pure technical depth; candidate must be able to work with stakeholders outside the team
• Described ideal profile as: collaborative, polished, well-educated, with breadth across infrastructure/applications/data
• Most of the current team has degrees from Northwestern, U of Chicago, etc.; a strong academic pedigree is valued
• Financial services background is helpful (regulated environment can be a culture shock) but not required

Tech Stack

• AI models: Anthropic Claude (primary); OpenAI GPT also familiar
• Infrastructure: AWS
• Data layer: Greenfield - “knowledge substrate” concept pioneered by CTO Matt Rathbun; not yet implemented, AWS-based likely
• Databricks being introduced by another team; may be relevant

AI research and engineering, strong python sql api cloud infrastructure aws docker cicd containerization claude the anthropic api or claude ai console designing agent orchestration or model context protocol based integrations ai applications and/or infrastructure, * Required: Strong Python; proficient SQL; solid distributed systems and API design fundamentals

• Required: Hands-on experience building LLM-powered applications or agentic systems
• Required: Working knowledge of AI-specific risk areas (prompt injection, output validation, hallucination mitigation, data privacy), or demonstrated ability to build this expertise quickly
• Required: Cloud infrastructure experience (AWS preferred); comfort with Docker, CI/CD, and containerization fundamentals
• Preferred: Direct experience with Claude, the Anthropic API, or Claude.ai/Console
• Preferred: Experience designing agent orchestration or Model Context Protocol (MCP)-based integrations
• Preferred: Production experience operating LLM-powered applications or agentic systems at scale
• Preferred: Kubernetes and infrastructure-as-code (Terraform)
• Preferred: Background in financial services, derivatives, or other regulated industries
• Preferred: Exposure to AI security practices such as red-teaming or adversarial testing of model inputs and outputs
• Preferred: Data engineering experience (pipelines, data modeling), particularly for candidates interested in AI infrastructure work