Staff+ Software Engineer, AI

Accountabilities

• • Own the shared AI foundation used by product engineering teams, including model selection and routing, model proxy infrastructure, context management, and tool design.
  • Design and evolve the architecture that allows different AI capabilities and product teams to build on a consistent, reliable foundation.
  • Own AI evaluation infrastructure, working with customers and finance-domain experts to define quality standards and translate them into repeatable evaluations.
  • Establish evaluation practices that teams can run consistently to measure model and agent performance and identify regressions or opportunities for improvement.
  • Build and ship agentic capabilities end to end, from initial proof of concept through production deployment and iterative optimization.
  • Apply prompt and context engineering, caching, parallel tool calls, subagent patterns, and other techniques to improve agent performance and efficiency.
  • Build observability into agent behavior, enabling teams to profile workflows, identify bottlenecks, diagnose failures, and prioritize improvements using data.
  • Monitor developments in agentic AI systems and selectively introduce proven techniques and engineering practices into production workflows.
  • Create proof-of-concepts rapidly, validate technical approaches, and turn successful concepts into production-ready v0 implementations.
  • Drive adoption of shared systems across teams through strong technical design, usability, reliability, and clear documentation.
  • Make pragmatic architectural decisions that balance long-term foundations with the need to ship incrementally.
  • Maintain high standards for code quality, correctness, readability, reliability, and maintainability across the systems you build.
  • Influence engineering practices beyond your immediate scope and provide technical leadership without relying on formal management authority.
  • Communicate complex technical decisions clearly and persuasively with both engineering and non-technical stakeholders.

  Requirements

  • Demonstrated experience building and shipping production LLM systems, including areas such as evaluation infrastructure, context management, multi-model routing, or multi-provider architectures.
  • Strong practical understanding of what can go wrong in production AI systems, with the ability to explain specific failures, trade-offs, and improvements you have implemented.
  • Experience with LLM APIs and agent frameworks, ideally combined with a track record of shipping user-facing AI products.
  • Strong understanding of prompt engineering, context design, tool use, agent orchestration, caching, and related techniques for production AI systems.
  • Experience designing and implementing evaluation methodologies that establish measurable quality standards for LLM or agentic systems.
  • Strong architectural judgment, with the ability to create clear abstractions while avoiding unnecessary complexity.
  • A highly pragmatic approach to engineering, with a preference for simple, effective solutions and incremental delivery.
  • Strong full-stack engineering fundamentals, including the ability to trace requests across user interfaces, services, APIs, and data stores and make sound technical decisions at each layer.
  • Demonstrated high agency, ideally developed through experience as a founder, engineering lead, startup builder, or similarly autonomous engineering role.
  • Track record of influencing adoption beyond your immediate team, with other engineers or product teams choosing to use systems you have built.
  • Deep commitment to engineering craft, including writing correct, understandable, maintainable, and high-quality code.
  • Excellent communication skills, with the ability to be clear, direct, persuasive, and effective across technical and non-technical audiences.
  • Experience building complex B2B products, ideally from the ground up.
  • Strong product mindset and customer orientation, with the ability to connect technical decisions to real user and business outcomes.
  • Motivated by shipping production systems and solving practical engineering problems rather than focusing primarily on academic or exploratory research.
  • Comfortable working autonomously in a remote-first environment and collaborating effectively across distributed teams in the Americas.
  • Based in the Americas and able to align reasonably with the team's working hours.

  Benefits

  • Fully remote work across the Americas.
  • Competitive compensation structure with location-based salary ranges and equity participation.
  • Flexible working hours designed to support autonomy and effective remote collaboration.
  • Unlimited paid time off.
  • Regular in-person company retreats and opportunities to build relationships with distributed teammates.
  • Company-provided MacBook Pro or Lenovo laptop.
  • Health insurance for eligible US and Canadian employees.
  • Guideline 401(k) program for eligible US employees.
  • Opportunity to work on production AI systems at the intersection of Generative AI, agentic workflows, and financial planning.
  • Significant technical ownership and the opportunity to influence architecture and engineering practices across multiple product teams.
  • Remote-first environment with a strong focus on autonomy, craftsmanship, pragmatic execution, and high-impact work.
  • Equal-opportunity workplace committed to diversity, inclusion,