Senior Backend Engineer (AI & Distributed Systems)

Location: Remote (USA) / Major Tech Hubs

About the Opportunity We are seeking a seasoned Senior Engineer to spearhead the evolution of a sophisticated enterprise platform by integrating advanced AI capabilities with robust distributed systems. This is a high-impact role where you will bridge the gap between traditional backend excellence and the frontier of production-grade AI orchestration. You will move beyond simple prototypes to build reliable, high-scale systems that leverage agentic workflows and complex data pipelines to drive tangible business outcomes.

Responsibilities

• System Ownership: Lead the complete lifecycle of customer-centric features, from initial architectural design and estimation to deployment and ongoing production maintenance.

• AI Orchestration: Architect and maintain production-level Large Language Model (LLM) integrations, including the development of retrieval-augmented generation (RAG) pipelines and automated agentic workflows with human-in-the-loop safeguards.

• Reliability & Governance: Implement rigorous evaluation frameworks for mixed deterministic and probabilistic systems, ensuring high standards for observability, security, and behavioral regression testing.

• Architectural Evolution: Define and enforce strict API contracts and data schemas while strategically modernizing legacy components to enhance system maintainability and development velocity.

• Engineering Excellence: Champion superior coding standards through the creation of pragmatic abstractions, comprehensive documentation, and a culture of meaningful automated testing.

• Operational Integrity: Manage model lifecycles and prompt engineering performance, establishing quantitative benchmarks to ensure all AI outputs meet strict acceptance criteria.

Requirements (Must-have)

• Professional Experience: Typically 7+ years of experience delivering scalable production software in customer-facing environments.

• Backend Mastery: Expert-level proficiency in C#/.NET or a similar enterprise-grade stack, with a deep understanding of concurrency, performance tuning, and data modeling.

• Distributed Systems: Proven track record of designing distributed services with a focus on versioning discipline and backward compatibility.

• Data Expertise: Advanced SQL skills (PostgreSQL or SQL Server), including complex schema design and query optimization.

• AI Integration: Experience combining traditional code with probabilistic model outputs via validation layers, guardrails, and structured enforcement.

• Infrastructure: Proficiency in cloud-native environments (Azure, AWS, or GCP) and containerization strategies.

• Problem Solving: Exceptional debugging skills with a relentless focus on root cause analysis and sustainable architectural fixes.

Preferred Qualifications (Nice-to-have)

• Advanced AI Implementation: Experience shipping production-ready RAG pipelines, vector search implementations, and multi-step tool-calling workflows.

• AI Observability: Familiarity with tracing prompts, monitoring inference costs/latency, and detecting model drift.

• Regulated Industries: Background building software within frameworks requiring high levels of auditability or regulatory compliance.

• Frontend Literacy: Competency in TypeScript frameworks (such as React) and a pragmatic approach to end-to-end testing strategies (e.g., Playwright).

• DevOps Mindset: Experience with Infrastructure-as-Code and maturing CI/CD pipelines.