AI Engineer, Agent Infrastructure

The SpringCube team curated the following job opportunity to help you in your job search. Explore the position below to find your next career move.

Company Overview

A fast-growing financial technology company is building an AI-native digital banking platform designed to expand access to premium financial services for young professionals in global markets. The organization was founded by experienced engineers and entrepreneurs with backgrounds spanning banking and high-growth technology companies. Its team has previously built and exited a successful payments company and is supported by prominent global technology investors.

The organization is developing technology intended to modernize traditional banking experiences and make financial services more accessible to emerging consumer markets.

The company is seeking an AI Engineer, Agent Infrastructure to own the infrastructure layer supporting production AI agents. This is an infrastructure-focused engineering role centered on the systems and architecture that enable AI agents to execute tasks, interact with tools, access internal and external systems, operate within defined permission boundaries, and perform reliably in production.

The successful candidate will work at the intersection of backend infrastructure and product engineering. The systems developed in this role will help establish how AI capabilities are deployed and integrated throughout the organization.

Key Responsibilities

• Build and own the execution layer for AI agents, including task orchestration, tool calling, and state management.
• Define how AI agents interact with internal systems and external APIs.
• Design sandboxed environments and permissioning models that enable safe and controlled agent execution.
• Develop evaluation, monitoring, and debugging infrastructure for production AI agent behavior.
• Integrate AI agents into real product workflows where correctness, reliability, and consistency are critical.
• Improve system performance while balancing latency, cost, and quality.
• Develop infrastructure that supports reliable and scalable deployment of AI agents.
• Collaborate across backend infrastructure and product teams to integrate AI capabilities into core workflows.

Required Qualifications

• Direct experience shipping production LLM or AI agent systems end-to-end, including orchestration, evaluation, and reliability.
• Strong foundation in backend or infrastructure engineering, including distributed systems, APIs, and platform engineering.
• Experience with workflow orchestration, automation systems, or AI agent frameworks.
• Familiarity with evaluation and observability systems for AI applications.
• Ability to consider both infrastructure requirements and product behavior when designing systems.
• Strong understanding of reliable production software development and system architecture.

Preferred Experience

• Experience building AI agent systems capable of taking real-world actions rather than simply generating text.
• Experience designing execution environments such as task runners, sandboxes, or job systems.
• Experience embedding AI deeply into customer-facing products or production applications.
• Experience building observability and evaluation loops for AI systems operating in production.
• Experience balancing system reliability, performance, cost, and quality in AI infrastructure.

Disclaimer

SpringCube curates tech job listings from various company websites to support tech professionals globally.

1. No Endorsement: Job ads on SpringCube do not imply endorsement of their authenticity or quality.
2. No Client Relationship: This company is not a client of SpringCube unless stated.
3. To Apply: Click the Apply button to be redirected to the hiring company’s application page for this job.
4. No Liability: SpringCube is not liable for inaccuracies.