Manager, Software Engineering (AI Platform Engineering )
The Opportunity
The GSmart AI platform is Ripple Treasury's production AI middleware layer — the infrastructure that enables generative AI capabilities across the entire product suite. As Manager of AI Platform Engineering, you will own this platform end-to-end: building new AI inference endpoints, writing prompts and evaluations, and expanding generative AI integration into solution areas that haven't previously used AI. You will also build and lead a team of up to four engineers.
This is a hands-on leadership role where you will write code and ship features alongside your team while defining the technical direction of AI across Ripple Treasury.
What You'll Do
Own the GSmart AI platform — design, build, operate, and evolve the production AI middleware serving enterprise treasury clients, including inference endpoints, prompt pipelines, and context engineering architecture.
Build and lead a high-performing team of up to four AI platform engineers, coaching direct reports, managing performance, and fostering a culture of engineering rigor.
Write and maintain production prompts using context engineering principles — structured prompt design and data transformation rather than retrieval-augmented generation.
Build evaluation frameworks as first-class engineering — create eval rubrics, golden datasets, LLM-as-a-judge pipelines, and CI/CD-integrated quality gates for every AI feature.
Partner with authorities across treasury domains (cash forecasting, payments, risk management) to understand business logic and build domain-accurate evaluations.
Advocate for generative AI adoption across Ripple Treasury solution areas, educating product and engineering teams on what AI can and cannot do in regulated financial contexts.
Operate and maintain cloud infrastructure — Azure Container Apps, API Management, Key Vault, Redis, and Langfuse observability for the AI platform.
Ensure compliance with AI governance frameworks relevant to regulated financial services, including ISO/IEC 42001, EU AI Act, and SWIFT CSCF.
Drive AI-assisted engineering practices — champion daily use of AI coding tools (Claude Code, Copilot, Cursor) across the team and broader engineering organization.
Recruit exceptional engineers — partner with talent acquisition to identify, interview, and hire AI platform engineers as you scale the team.
What You Bring
7+ years of software engineering experience with at least 2 years building and operating AI/ML systems in production environments (not prototypes or demos)
2+ years of engineering management experience, including hiring, coaching, and growing engineers
Hands-on experience with LLM-based systems in production — prompt engineering, inference optimization, and production monitoring at scale
Strong evaluation engineering skills — experience building golden datasets, eval rubrics, or automated evaluation pipelines for AI system quality
Cloud infrastructure expertise — experience deploying and operating containerized services on Azure (or equivalent cloud), including CI/CD pipelines
Proficiency in Python for AI workflows (agentic flows, context engineering, data transformation) and familiarity with .NET backend systems
Experience collaborating with domain experts to translate business knowledge into AI system design and evaluation criteria
Excellent communication skills — ability to explain AI capabilities and limitations to non-technical partners in clear, concrete terms
Comfort working in regulated environments where outputs must be accurate, auditable, and trustworthy
Nice to Have
Experience with the specific tech stack: Azure OpenAI (GPT-4.1), LiteLLM proxy, Langfuse, Azure Container Apps, Redis
Familiarity with AI governance frameworks (ISO/IEC 42001, EU AI Act, NIST AI RMF) or model risk management practices
Background in financial services, treasury, or enterprise SaaS
Experience building context engineering architectures (as distinct from RAG)
Contributions to AI evaluation tooling or open-source AI infrastructure projects