Staff Engineer or Architect (AI Agentic Team)
Posted Updated
- Reporting to the Director of Software Engineering, the Staff Engineer or Architect (Agentic AI Team) will be responsible for designing, building, and owning agent systems end-to-end - from design through production
- This role involves building reliable, steerable, multi-step agent workflows that plan, execute, observe outcomes, and iteratively improve
- This role is expected to leverage AI and emerging technologies to improve productivity, enhance decision-making, and continuously optimize how work is performed
- Design, build, and own agent systems end-to-end - from design through production - for identity, fraud, risk, and commerce workflows. You own the eval harness and observability for what you ship, not just the happy path
- Build reliable, steerable, multi-step agent workflows that plan, execute, observe outcomes, and iteratively improve - including tool use and human-in-the-loop patterns appropriate to regulated, high-stakes decisions
- Troubleshoot novel, non-deterministic failures across models, tools, orchestration, and infrastructure. You stay calm under ambiguity, form hypotheses, instrument the system, and find the root cause
- Work in a compliance-heavy, globally regulated domain where auditability, correctness, and human oversight are features, not afterthoughts
- Set and communicate a technical vision - to teammates and to the agents you direct. You make the implicit explicit: a spec an agent can execute is a spec a teammate can trust
- Leverage AI and emerging technologies to improve productivity, streamline workflows, and identify opportunities for continuous improvement while ensuring the responsible, secure, and compliant use of AI tools
- Orchestrate AI agents in your daily work and hold the bar on what they produce. You keep a clear mental model of the system, verify what changed, and stay accountable - AI is a force multiplier, not an excuse
- Demonstrated ability to own features end-to-end and communicate trade-offs clearly to both technical and non-technical stakeholders
- Fluency using AI agents in your own engineering workflow - you can show us how you keep a mental model, verify outputs, and stay accountable while moving faster with AI
- 8+ years of software engineering experience with demonstrated impact on production systems
- Experience working on challenging, novel, or ambiguous projects where you had to define the problem, not just solve a handed-down spec
- Hands-on experience building with LLMs - prompt engineering, RAG, tool use, and at least one agent framework (e.g. LangGraph, CrewAI, AutoGen, or similar), plus evaluation frameworks for agent behavior
- If you don’t see yourself fully reflected in every job requirement listed on the posting above, we still encourage you to reach out and apply
- Vector databases, knowledge graphs, or structured retrieval for agent memory
- AI observability tooling; MLOps practices (experiment tracking, model registries, feature stores)
- Experience in financial services, identity, fraud, or risk domains, or other compliance-heavy environments (AML, fraud rules engines, identity graphs, risk scoring)
- Multi-agent orchestration patterns and production-grade evaluation harnesses
- Recruiter Interview: 30 Minutes
- Hiring Manager Interview: 30 Minutes
- Technical Interview: 120 Minutes
- Final Leadership Interview: 30 Minutes