Staff Full-Stack Software Engineer (AI & App Experience)

• Chime is looking for an Engineering Manager to lead one of the teams building Jade, our AI-powered financial assistant, within the AI & App Experience (AAX) organization
• AAX is building the next generation of the Chime member experience, and Jade sits at the center of it: helping millions of members manage their spending, stay on top of subscriptions, and reach their financial goals through conversation that’s natural, reliable, and trustworthy
• We’re looking for a Staff Software Engineer to help design, build, and ship member-facing AI capabilities
• As a Staff engineer on the team, you’ll set the technical direction for how we build with LLMs, architecting the agent systems, evaluation frameworks, and guardrails that let us ship an AI product reliably and safely at the scale of millions of members
• You’ll stay deeply hands-on: designing new agent capabilities and conversation experiences, prototyping quickly, and shipping production code, while raising the technical bar for the engineers around you
• You pair strong engineering fundamentals with a product mindset, owning capabilities from problem definition through measurement and iteration
• The AI landscape evolves rapidly, so does Chime
• You’ll need to learn quickly, adapt to shifting priorities, and proactively identify what’s needed next, whether that’s a new financial capability, a better way to evaluate conversations, or a system to keep quality high as we scale
• If you’re excited by the unique challenges of building LLM-powered products at scale, this is the role for you
• Set the technical direction and architecture for how Chime builds with LLMs on Jade: the agent architectures, prompt strategies, and orchestration patterns that shape how Jade reasons and acts, and that other engineers build on
• Design, build, and scale new member-facing capabilities for Jade, from prototype through production, moving fluidly between product discovery and hands-on engineering
• Build the eval frameworks, observability, and guardrail systems that let the team ship LLM-powered features with speed, safety, and confidence
• Develop and harden the backend services and internal tooling behind Jade (model routing, prompt management, agent orchestration, and evaluation pipelines), improving reliability and performance as we scale
• Leverage AI and LLMs natively in your own workflow, using AI-assisted coding and rapid prototyping, and turn one-off AI workflows into reusable systems (agent loops, evals, custom tooling) that compound the whole team’s output
• Champion AI-native development practices across the team: set the quality gates that keep AI-assisted output production-ready, encode recurring failure modes into shared evals and guardrails, and push the team to work at the frontier of what AI tooling makes possible
• Exercise judgment about where and how AI is applied, deciding which problems get an AI-generated first pass and which need human judgment, and calibrating model autonomy to the stakes and reversibility of each decision
• Drive experimentation and rapid iteration: design A/B tests, analyze results, and make data-informed decisions about what to scale, pivot, or kill
• Partner cross-functionally with product, design, data science, and risk to understand member pain points and deliver secure, scalable solutions
• Contribute to technical design and uphold high standards across the codebase through code reviews and mentorship, multiplying the impact of the engineers around you
• Participate in on-call rotation; being on call may include responding to incidents outside of regular working hours when necessary

Benefits

• Physical: We believe in taking care of your physical health, so as a Chimer you’ll get medical, dental, and vision insurance, as well as benefits to support your physical activity, family planning, and all of your little Chimers
• Emotional: We know that staying healthy involves a lot more than doctor’s checkups. We partner with Modern Health to help you navigate your mental health, give monthly Take Care of Yourself Days, and want you to take time off when you need it
• Financial: We want Chimers to save and feel financially supported, so we offer savings plans with competitive matching, as well as access to financial planning and legal assistance so that you can find your financial peace of mind
• Social: We’ll celebrate your milestones together with travel stipends, swag, and high-fives and make sure you’re connected to fellow Chimers through our Chime Resource Groups (CRGs) and company events- Proficiency with Python or comparable frameworks, with the breadth to make sound decisions across the stack
• AI-native fluency: you actively build with LLMs, AI code assistants, and generative AI tooling as a daily part of your workflow, not as a side project
• Hands-on experience building or shipping LLM-powered product features (agents, conversation experiences, evals, prompt strategies, or guardrails) at production scale
• A track record of mentoring engineers and raising the technical bar
• 8+ years of backend or full-stack software development experience in production environments
• Bonus: experience with agent development, fintech, or startup environments
• A product mindset with a bias toward action: you ship v1 fast, learn from real usage, and iterate, letting data settle debates
• Demonstrated technical leadership across teams: setting direction, driving architectural decisions, and aligning cross-functional stakeholders without relying on positional authority
• Deep expertise in system design, distributed systems, and architectural patterns for high-scale systems
• Experience with transactional databases (e.g., Postgres) and caching systems (e.g., Redis), and a strong focus on writing maintainable, well-tested code
• Sound judgment about where and how to apply AI, calibrating verification effort and model autonomy to the stakes, reversibility, and cost of each task
• A track record of turning AI into durable leverage: reusing and improving workflows, encoding recurring fixes into evals, rules, and tooling instead of solving the same problem twice, and acting as the first and most critical reviewer of AI-generated output