AI Backend Engineer (AI Workflow Systems)
This position is listed on behalf of a partner company, who manages all applications and next steps. Our partner is looking for an AI Backend Engineer (AI Workflow Systems) based in the United States.
This role sits at the core of building and operating production-grade AI systems that power real-world insurance and financial workflows.
You will design backend infrastructure that orchestrates AI models, APIs, and business logic into reliable end-to-end automation systems.
The position focuses on delivering high-performance AI workflows where latency, scalability, and correctness directly impact user experience.
You will work across distributed systems, connecting machine learning outputs with backend services and product-facing applications.
A key part of the role involves building and optimizing inference pipelines for LLM-based and AI-assisted automation features.
You will also ensure system reliability through strong observability practices, production debugging, and incident response ownership.
This is a high-impact engineering role in a fast-moving environment where AI systems are deployed at global scale.
Accountabilities:
- Design, build, and operate backend systems that power AI-driven insurance and workflow automation in production.
- Develop AI orchestration layers that connect LLMs, APIs, backend services, and business logic into unified systems.
- Build and optimize inference pipelines for LLM-based and AI-assisted workflows, including batching, caching, and routing strategies.
- Ensure system reliability through observability practices such as logging, monitoring, tracing, and alerting.
- Debug and resolve production issues across distributed AI systems, identifying root causes and implementing long-term fixes.
- Define and maintain stable service boundaries between backend, ML components, and product APIs.
- Collaborate closely with product, frontend, operations, and ML teams to deliver end-to-end AI features.
- Continuously improve system performance, scalability, cost efficiency, and operational stability.
- Strong backend engineering experience building production-grade distributed systems.
- Hands-on experience with high-throughput, low-latency services and scalable backend architectures.
- Familiarity with AI systems such as LLMs, embeddings, or AI-powered workflows.
- Solid understanding of system design principles, APIs, and data flow architecture.
- Experience working with observability tools including logging, metrics, tracing, and monitoring systems.
- Strong debugging skills with the ability to diagnose and resolve production issues in distributed environments.
- Proficiency with backend technologies such as Python or Node.js.
- Experience working in fast-paced, high-ownership, globally distributed engineering teams.
- Strong ownership mindset with a focus on shipping reliable production systems.
- Competitive salary package aligned with experience and market standards
- Fully remote work with global engineering collaboration
- Opportunity to build and scale production AI systems used across real-world insurance workflows
- Learning and development support for continuous technical growth
- High-ownership engineering culture with end-to-end system responsibility
- Exposure to modern distributed systems and AI infrastructure stacks
- Career growth opportunities in a fast-scaling global engineering organization
- Work on impactful AI products used by millions of users internationally