Senior AI Engineer

TL;DR

Senior AI Engineer (Python/C#/RAG): Building scalable backend services for intelligent document processing, context grounding, retrieval, and AI agents with an accent on distributed systems, cloud-native platforms, and production AI applications. Focus on designing APIs and microservices, implementing retrieval and vector-search capabilities, and operating reliable services at enterprise scale.

Location: Bellevue, United States. Work arrangements may be hybrid, office-based, or remote depending on business and role requirements.

Company

Enterprise software company developing automation and AI platforms that help organizations understand information and automate business processes.

What you will do

• Design, develop, and operate scalable backend services for document ingestion, parsing, extraction, retrieval, knowledge management, and AI orchestration.
• Build cloud-native distributed systems that process large volumes of enterprise content with strong scalability, reliability, security, observability, and performance.
• Develop production AI capabilities using LLMs, retrieval systems, vector search, embeddings, and document processing.
• Design and integrate APIs, event-driven services, messaging, caching, databases, and evaluation pipelines.
• Collaborate with product managers, applied scientists, designers, and engineers through architecture discussions, design reviews, code reviews, and technical planning.
• Own features from design through production and make technical decisions in ambiguous problem spaces.

Requirements

• 6+ years of professional software engineering experience.
• Strong backend engineering experience building distributed systems, scalable APIs, and microservices.
• Production experience with Python and/or C#.
• Experience building cloud-native applications on Azure, AWS, or GCP.
• Strong understanding of distributed systems, concurrency, networking, software architecture, event-driven systems, messaging, caching, and databases.
• Excellent debugging, problem-solving, communication, and technical ownership skills.

Nice to have

• Experience with generative AI, RAG, LLM-powered applications, semantic search, vector databases, OCR, intelligent document processing, search infrastructure, or knowledge management platforms.
• Experience with Azure, Docker, Kubernetes, Azure OpenAI, embeddings, and search platforms.

Culture & Benefits

• Work on production AI infrastructure used for enterprise automation and AI agents.
• Flexible work arrangements may be available depending on business and team needs.
• Collaborative environment focused on technical learning, ownership, engineering quality, and measurable customer value.
• Inclusive workplace with equal opportunities and reasonable accommodations for candidates.
• Applications are reviewed on a rolling basis, with no fixed deadline.