Lead AI Back-End Engineer

For our client, we are seeking a Lead AI Back-End Engineer to join the team of a leader in the Enterprise Technology space. This role will lead the architecture and delivery of an agent-powered platform, with a strong focus on LLMs, retrieval technologies, and high-performance backend services. You will partner closely with engineering teams to shape technical direction, improve platform reliability, and translate business goals and user feedback into scalable solutions. The position also plays a key role in advancing engineering standards around governance, cost optimization, and AI-driven productivity. Location: Remote - US based candidates only, no visa sponsorship available Compensation: $138,000 – $165,000 annually Responsibilities Set the technical architecture for an agent-powered platform, focusing on LLMs and retrieval technologies. Drive the development of high-throughput APIs using .NET, C#, and Python frameworks from design to production. Lead multi-agent orchestration processes, ensuring effective coordination and execution of tasks across varied agent frameworks. Guide teams in implementing Retrieval Augmented Generation on enterprise search platforms, ensuring effectiveness and safety. Oversee end-to-end CI/CD pipeline processes, ensuring code quality, testing, and deployment best practices are followed. Mentor and hire engineers while integrating AI coding agents to enhance productivity and maintain strong code quality standards. Promote observability and FinOps for LLM workloads to maintain performance and cost-efficiency. Qualifications 7+ years of experience in building and scaling production backend systems, with 2+ years in a technical lead, staff, or principal role. Expertise in REST API design using Python FastAPI or .NET C#, with a focus on performance optimization and distributed systems. Experience leading projects with Semantic Kernel or similar LLM frameworks, including production agent orchestration and multi-step workflows. Designed and implemented at least one production RAG system using vector or hybrid search platforms with measurable performance metrics. Deep understanding of PostgreSQL along with SQLModel, SQLAlchemy 2, and migration strategies at scale. Proven experience integrating multiple AI model providers, managing complex routing and fallback strategies. Familiarity with containerization and CI/CD tools, including Docker, GitHub Actions, and Jenkins. Benefits Opportunity to work on cutting-edge AI technologies that serve millions of users. Chance to steer the architecture and engineering culture of a leading AI platform. Collaborative environment focused on mentoring and developing strong engineering talent. Involvement in shaping the technical roadmap linked to business goals and user feedback. Focus on enterprise-grade standards for reliability, security, governance, and cost optimization. Our client is an equal opportunity employer. We encourage you to apply even if you don’t meet every qualification—your background could be exactly what this team needs.