Staff Software Engineer, GenAI Platform

THE WORK

At Ripple, we’re building a world where value moves like information does today. You’ll collaborate with world-class colleagues to successfully implement innovative solutions that redefine the global financial system.

WHAT YOU’LL DO

• Develop and deliver production-quality agentic AI systems end-to-end using Python, Go, and/or Java, covering EKS deployment, agent runtimes, memory systems, orchestration, tool integration, and evaluation pipelines that operate across Ripple's polyrepo engineering environment.
• Define and advance Ripple's Enterprise Agentic AI and developer platform architecture through practical implementations, reference systems, and production deployments — not abstract diagrams.
• Build and implement multi-agent orchestration patterns (planner, executor, reviewer, tool agents) using frameworks such as LangGraph, MCP, Claude Code agent harnesses, or similar orchestration systems, with strong regression coverage and observability.
• Run fast, high-quality POCs on emerging agent architectures; harden successful patterns into reusable platform services, APIs, SDKs, and developer templates that engineering teams across Ripple can adopt.
• Architect and implement data flywheels that continuously improve agent quality through telemetry, benchmarking, automated evaluation, and structured feedback loops — treating quality, cost, latency, and safety as first-class signals.
• Earn security, guardrails, sandbox isolation, auditability, and policy enforcement directly into agent runtimes in partnership with security, compliance, and governance teams — particularly for workflows that touch XRPL, RLUSD, and payment systems.
• Evaluate, integrate, and extend open-source and third-party agent platforms; drive disciplined build-vs-use decisions based on performance, scalability, control, and long-term platform ownership.
• Collaborate closely with engineering, infrastructure, product, and business partners to align architectural direction with enterprise priorities and accelerate adoption across the organization.

WHAT YOU’LL BRING

• Bachelor's degree in Computer Science or related field or equivalent experience; Master's or PhD preferred.
• 10+ years of experience building and shipping large-scale distributed systems with significant hands-on coding in Python, Go, Java, or similar systems languages.
• Proven ability to move quickly from idea to functional prototype to robust, scalable platform solution.
• Proven track record in constructing agentic AI systems, including RAG pipelines, long-lived memory models, multi-agent orchestration (e.g., AgentCore, Strands, LangGraph, MCP, Claude Code, LangChain), tool frameworks, and evaluation infrastructure.
• Expert-level depth in Kubernetes (EKS preferred), service mesh (Istio), containerized workloads, networking, APIs, and secure enterprise integration patterns.
• Experience crafting benchmarking, regression testing, telemetry, and observability systems (OpenTelemetry, Prometheus, Grafana) that measure agent quality, latency, cost, reliability, and safety.
• Strong understanding of performance tuning in hybrid environments, including managed inference endpoints and GPU-based workloads.
• Excellent collaboration skills with the ability to influence cross-functional partners, build positive relationships, and clearly communicate complex architectural concepts to both technical and business audiences.

PREFERRED QUALIFICATIONS

• Proven experience delivering reusable developer-acceleration components such as SDKs, APIs, templates, reference implementations, and CI/CD automation.
• Experience building cross-repo context engines or AI-native developer platforms at scale (vector databases such as Qdrant, code embeddings, Tree-sitter, retrieval across thousands of repositories).
• Experience integrating enterprise agentic search and orchestration platforms (Glean, Cursor, Claude Code at organizational scale, Microsoft Copilot Studio, or similar).
• Experience embedding fine-grained policy enforcement, access controls, sandbox isolation, and audit trails directly into AI runtimes — particularly in regulated or financial contexts.
• Familiarity with formal methods (TLA+, model checking) or property-based testing applied to agentic systems and distributed protocols.
• Background in blockchain, payments infrastructure, or the XRPL/RLUSD ecosystem.
• Evidence of meaningful open-source contributions: core commits, maintainer-ship, widely adopted libraries, or public technical artifacts demonstrating system-level depth.