Senior Software Engineer, Backend - Platform (Core AI Automation)

Ready to do the most impactful work of your career? At Coinbase, we are uncompromising on our mission to increase economic freedom. The bar is high, the environment is intense, and we like it that way. This isn't a place for complacency, it’s a place to be pushed past your perceived limits. If you're ready to build the future of finance alongside people who refuse to settle for "good enough," you belong here. Coinbase is a remote-first, but not remote-only company. Expect to get together quarterly for intense in-person working sessions called “surges.” learn more about working at Coinbase.

As a Senior Software Engineer on the Platform Core Automation team, you'll build the AI infrastructure and agentic systems that automate customer support and compliance operations at Coinbase. This team is reimagining what these processes look like when AI handles them end-to-end, replacing manual workflows with intelligent agents that resolve customer issues and execute compliance tasks autonomously. You'll own the design and delivery of LLM-powered systems, grounding techniques, and integration pipelines that directly reduce resolution times, cut costs, and improve accuracy across millions of customer interactions.

What you’ll be doing (ie. job duties):

• Own the design and delivery of agentic AI systems that power Coinbase's customer support and compliance automation, from LLM orchestration through production deployment and monitoring.
• Build scalable, secure backend infrastructure in Python and Golang that serves AI workloads, including model integration pipelines, guardrails, grounding mechanisms, and measurement frameworks.
• Drive end-to-end project execution on complex AI initiatives, making technical trade-offs across latency, accuracy, cost, and reliability.
• Partner with Customer Experience, Compliance, and product engineering teams to identify high-impact automation opportunities and translate operational pain points into AI-powered solutions.
• Strengthen engineering quality across the team by leading code reviews, mentoring engineers on AI system design patterns, and contributing to on-call rotations and incident response.

What we look for in you (ie. job requirements):

• 5+ years of experience in software engineering, with proven expertise in designing, building, and maintaining production services using a microservices architecture.
• Hands-on experience building LLM-based applications or AI/ML systems in production, including prompt engineering, retrieval-augmented generation (RAG), or agentic AI frameworks.
• Proficiency in Python and Golang (or comparable backend languages), with experience integrating third-party AI models and APIs into production workflows.
• Track record of delivering end-to-end projects with measurable business impact in ambiguous problem spaces.
• Experience building data pipelines, integrating with external vendors, or working with large-scale unstructured data sources (e.g., blockchain data, customer interaction logs).
• Utilizes generative AI responsibly, maintaining human oversight to deliver business-ready outputs and drive measurable improvements in workflow efficiency, cost, and quality.

Nice to haves:

• Experience navigating rapid company growth (e.g., from startup to mid-size).
• Familiarity with GenAI frameworks/tools, Python, GoLang, Docker, Postgres, MongoDB.
• Background in AI/LLM infrastructure is a strong plus.