Join Deloitte's Technology & Transformation practice as a Backend/Platform Engineer, specializing in Agentic AI. You will be instrumental in building and scaling the core infrastructure for enterprise AI agents and applications within a regulated fintech environment. This role offers a unique opportunity to shape the future of AI deployment at scale, leveraging cutting-edge technologies.

We are seeking individuals with a strong foundation in software engineering, expertise in distributed systems, and a passion for cloud-native architectures. If you are driven to build robust, production-grade AI agent platforms, this is the role for you.

Design and implement backend services critical for agent creation, configuration, and execution, encompassing the full runtime stack. Develop robust orchestration capabilities for asynchronous processing, routing, and error handling across multi-agent workflows.

Integrate LLMs and Agent SDKs (e.g., Google ADK, LangGraph) via clean, scalable platform APIs. Connect AI agents with enterprise applications, ensuring seamless integration through versioned APIs. Build comprehensive production observability using OpenTelemetry, enabling end-to-end tracing across agent, model, tool, and service execution.

Deploy and manage platform services on Kubernetes (GCP/GKE) with a focus on security, CI/CD, scalability, and production reliability. Collaborate closely with cross-functional teams to deliver scalable enterprise AI solutions. Take full ownership of platform components from inception to continuous improvement.

We are looking for engineers with 4-6 years of experience in backend or platform engineering. Proficiency in Python is essential, along with hands-on experience building production backend services using frameworks like FastAPI.

Demonstrate a strong grasp of distributed systems, asynchronous programming, microservices, REST APIs, and scalable backend architectures. Experience with APIs, developer platforms, or orchestration systems is highly valued. Familiarity with AI agents or related technologies is a plus but transferable platform engineering skills are key.

Experience with cloud-native architecture on GCP/GKE, Kubernetes, and Docker is required. A solid understanding of CI/CD, security, production reliability, and cloud infrastructure practices is necessary. Proficiency in production observability, distributed tracing (e.g., OpenTelemetry), and databases (PostgreSQL, Redis) is important. Strong problem-solving, communication, and ownership skills are crucial for success in this dynamic environment.