Staff Software Engineer
Staff Software Engineer building and evolving Control Center, Coinbase's secure internal operations platform, into an AI-agent-ready system with MCP, agentic guardrails, and distributed backend services.
About the job
What you'll do
- Own the architecture and delivery of foundational platform capabilities including MCP tool registries, AI orchestration layers, risk-based access automation, and the away-team contribution model that enables product groups to build on Control Center safely and at speed.
- Drive the evolution of Control Center into an AI-agent-ready, headless operations platform by designing and implementing MCP procedure constructs, agentic guardrails, HITL orchestration, and evaluation frameworks for secure autonomous operations.
- Lead technical direction across the team in partnership with the Engineering Manager and Product, authoring TDDs, running design reviews, decomposing complex initiatives into deliverable milestones, and raising the engineering quality bar through code review and mentorship.
- Build highly reliable, secure distributed backend services, owning SLO definitions, observability instrumentation, incident response, and operational readiness for Tier-1 systems serving thousands of internal users and AI agents.
- Partner across EAA engineering, Product Engineering, and Security Engineering teams to deliver cross-functional outcomes and drive shared platform primitives that eliminate duplicated infrastructure.
Required Skills and Experience
- 8+ years of software engineering experience with a demonstrated track record architecting and delivering large-scale, high-traffic distributed systems, including deep proficiency in backend service design, API development (gRPC, MCP, GraphQL), and scalable microservices architectures.
- Proven ability to independently lead ambiguous, high-impact technical initiatives from whiteboard to production as a technical owner across complex, multi-team problem spaces, writing high-quality, well-tested code that sets the standard for others.
- Hands-on experience with cloud-native infrastructure including AWS, Kubernetes, Terraform, CI/CD pipelines, event-driven architectures (Kafka, MQ), distributed caching (Redis/Memcached), and SQL or NoSQL databases.
- Track record building secure, compliant internal tools or platforms with deep appreciation for security controls, access management, audit logging, and data governance in a regulated financial services environment.
- Experience building or integrating with agentic AI systems including MCP servers, LLM orchestration layers, RAG pipelines, HITL workflows, or evaluation and guardrail frameworks for production agentic workloads, with proficiency in Go and willingness to work across Python.
- Utilizes generative AI responsibly, maintaining human oversight to deliver business-ready outputs and drive measurable improvements in workflow efficiency, cost, and quality.
Skills
Go, Python, AWS, Kubernetes, Terraform, Kafka, Redis, gRPC, GraphQL, Mcp
Similar jobs
Backend Engineering jobsStaff Software Engineer building distributed backend platforms and infrastructure for customer service and compliance workflows. The role requires 8+ years of experience, deep Go expertise, cloud and DevOps skills, architectural leadership, and engineer mentorship.
Own and evolve Coinbase’s large-scale application routing infrastructure across Kubernetes, Envoy, and Istio. The role requires 8+ years in software and infrastructure engineering, strong systems programming and AWS experience, and expertise in distributed systems and service networking.
Leads the architecture and development of production agentic AI systems, distributed infrastructure, APIs, orchestration, guardrails, and evaluation frameworks for scalable automation. Requires 8+ years of software engineering experience and demonstrated expertise shipping AI/ML applications and reliable LLM-based systems.
Leads the architecture and hands-on development of internal developer platforms, AI-agent workflows, and distributed automation infrastructure. Requires 8+ years of software engineering experience, Staff-level technical leadership, and strong backend, microservices, and event-driven architecture expertise.
Designs and operates high-throughput, low-latency ad-serving infrastructure, including GPU-based model inference and feature stores. Requires 10+ years of industry experience, strong computer science fundamentals, and a master’s degree in computer science or equivalent experience.