# Staff Software Engineer, AI Platform — Ripple

- Location: Chicago, IL
- Posted pay: $208k–$260k/yr
- Posted: Aug 15, 2026
- Status: open (checked Nov 20, 2026)
- Apply (employer's site): https://ripple.com/careers/all-jobs/job/8129139?gh_jid=8129139
- Employer record: https://visajobs.io/company/ripple-labs.md

## Sponsorship history
- Tier: Good history
- Occupation (SOC): Software Developers (15-1252)
- Employer's certified LCAs for this occupation in IL, FY2024–FY2026: 1
- …in the whole US: 52
- With this exact title: 0
- Median DOL prevailing wage, level I / II: $85k / $107k

## Description
At Ripple, we’re building a world where value moves like information does today. It’s big, it’s bold, and we’re already doing it. Through our crypto solutions for financial institutions, businesses, governments and developers, we are improving the global financial system and creating greater economic fairness and opportunity for more people, in more places around the world. And we get to do the best work of our career and grow our skills surrounded by colleagues who have our backs.
If you’re ready to see your impact and unlock incredible career growth opportunities, join us, and build real world value.
The Opportunity
The mission, should you choose to accept it, is to pioneer and scale GSmart, Ripple Treasury's AI platform, into the future. If you enjoy solving complex business problems in a fast-paced, collaborative, and iterative environment this might be the right role for you!
We are seeking an innovative and forward-thinking Staff Software Engineer passionate about building a world-class AI platform through a world-class team. You will set the technical direction for how AI is built, measured, and operated across our enterprise treasury products, and stay hands-on in design, implementation, and production.
About the AI Platform Team
The AI Platform team builds and operates GSmart, the production AI platform behind the intelligent features in Ripple Treasury. Enterprise treasury teams in 160+ countries rely on it for forecasting, risk, onboarding, and analyst experiences.
GSmart is middleware, not a single feature. It gives every product team model routing, guardrails, observability, evaluation, and context injection out of the box, so each new AI capability is cheaper and safer to build than the last.
We're now extending the platform into an agentic layer: agents that reason over treasury data and act on behalf of finance teams, with the auditability that regulated financial workflows demand. We hold a high bar on measurement. If we can't evaluate it, we don't ship it.
What You'll Do – Be a Force Multiplier
Technical Leadership & Architecture:
Drive architectural decisions for the AI platform, balancing scalability, maintainability, cost, and rapid delivery
Establish the standards and design patterns for how teams build on GSmart: context assembly, prompt and model management, guardrails, and agent orchestration
Lead technical design reviews and give constructive feedback that elevates the team's architectural thinking
Identify and retire technical debt strategically, with roadmaps that improve both developer velocity and platform reliability
Evaluation & AI Quality:
Own the evaluation strategy for the platform: datasets, rubrics, automated and human review, and regression gates in CI/CD
Make AI quality measurable, so every prompt, model, or context change ships with evidence rather than opinion
Diagnose failure modes in production LLM systems and turn them into evals that prevent recurrence
Team Enablement & Mentorship:
Mentor mid-level and senior engineers, helping them grow into technical leadership roles
Break down complex, ambiguous problems into actionable work that distributes effectively across the team
Enable product teams to build on the platform and own their deliverables, through clear interfaces, documentation, and reference implementations
Champion engineering practices including observability, incident response, and production excellence
Strategic Technical Vision:
Anticipate scalability, latency, and cost challenges before they become blockers (e.g., 10x growth in inference volume or expansion into new data-residency regions)
Evaluate emerging models, frameworks, and agent patterns, and recommend when and how to adopt them
Balance technical excellence with pragmatic delivery, knowing when "good enough now" beats "perfect later"
Ownership & Accountability:
Own critical platform systems end-to-end, from design through production support
Take responsibility for production reliability and proactively prevent incidents
Step into ambiguous situations and drive them to resolution without needing explicit direction
Lead by example in code quality, documentation, and operational excellence
Make tough technical trade-off decisions and clearly communicate the reasoning
What You'll Work On
AI middleware — the shared services every AI feature runs through: model routing across providers, guardrails, memory, and context injection
Evaluation and observability — tracing, evals, prompt registry, experimentation, and cost tracking that make AI behavior visible and auditable
Agentic layer — the orchestration, tooling, and safety model for agents that work across treasury data and workflows
Regional deployment — infrastructure-as-code that brings inference and memory into new geographies while meeting data-sovereignty requirements
Product integration — partnering with Forecasting, Risk, Liquidity, and Digital Assets teams to turn customer problems into platform capabilities
Essential Knowledge / Experience
Years & Scope:
8+ years of professional software engineering experience
3+ years working on complex, business-critical systems in production
2+ years building and operating LLM-based systems in production, beyond proof of concept
Strong communication skills with experience working in cross-functional projects
Track record of delivering projects that span multiple quarters and require coordination across teams
Technical Leadership:
Led technical designs that were implemented by teams of 3+ engineers
Made architectural decisions that had lasting impact on system capabilities
Established technical patterns that were adopted across teams
AI Platform Engineering:
Has owned a production LLM platform or shared AI service used by multiple product teams
Can define and run evaluations: golden datasets, rubric and model-graded scoring, regression testing, and online monitoring
Understands context engineering and retrieval, and can explain when each is the right tool
Hands-on with model gateways 

> History, not a promise: past H-1B filings do not mean an employer will sponsor you or a given role. Data: U.S. DOL OFLC LCA disclosure (FY2024–FY2026 for role counts, certified LCAs) and the USCIS H-1B Employer Data Hub. Not legal advice. Methodology: https://visajobs.io/methodology
