Machine Learning Engineer (LLM inference)

GMI Cloud is seeking a Fullstack Engineer to build core systems for their global inference engine and MaaS platform. This role focuses on designing and scaling systems for AI delivery, requiring expertise in backend systems and distributed infrastructure. Responsibilities: Design and evolve a globally distributed inference engine and MaaS platform, spanning API gateways, routing, orchestration, scheduling, and multi-region traffic management for high-concurrency production workloads; Build end-to-end fullstack systems—including backend services, APIs, and web applications—that provide developers with seamless control, visibility, and scalability over AI workloads; Architect and operate high-throughput, low-latency distributed systems with strong guarantees on reliability, fault tolerance, and graceful degradation under extreme load; Develop scalable data infrastructure across databases, caching systems, and streaming pipelines to support real-time usage tracking, analytics, and system observability; Design and implement robust billing, metering, quota, and payment systems that are accurate, auditable, and tightly integrated with platform usage at scale; Build intelligent platform capabilities using agentic software patterns, enabling automation, adaptive system behavior, and more efficient operation of complex infrastructure; Drive system-level performance optimization across concurrency control, request lifecycle, storage, and compute coordination to maximize throughput and efficiency; Establish engineering standards and architectures that prioritize system stability, correctness, and long-term maintainability in a rapidly evolving AI ecosystem Qualifications: Strong fullstack engineering experience with deep expertise in backend and distributed system design; Proven experience building and operating high-concurrency, large-scale distributed systems in production; Strong understanding of system design tradeoffs across scalability, consistency, availability, and performance; Hands-on experience with: Backend systems (Python, Go, or similar); Modern web stacks (React, Next.js, or equivalent); API design (REST, gRPC, GraphQL); Strong experience with databases and storage systems (PostgreSQL, MySQL, or similar), including high-scale schema design and optimization; Experience with caching systems (Redis or equivalent) and performance-critical system design; Familiarity with distributed system patterns such as load balancing, rate limiting, queueing, and multi-region deployment; Experience building billing, metering, or payment systems in production environments; Experience building or working with agentic software systems (e.g., automated workflows, tool-using systems, or LLM-powered orchestration); Strong debugging, profiling, and performance optimization skills; Clear communication skills and the ability to reason about complex systems end-to-end Required Skills: Fullstack engineering, Backend systems - Python, Backend systems - Go, Distributed system design, High-concurrency distributed systems, System design - scalability, Consistency, Availability, Performance, Modern web stacks - React, Modern web stacks - Next.js, API design - REST, API design - gRPC, API design - GraphQL, Databases - PostgreSQL, Databases - MySQL, Caching systems - Redis, Distributed system patterns - load balancing, Distributed system patterns - rate limiting, Distributed system patterns - queueing, Distributed system patterns - multi-region deployment, Billing systems, Metering systems, Payment systems, Agentic software systems, Debugging, Profiling, Performance optimization