Senior AI Engineer

About the role

The hire will own the design and delivery of production-grade AI services that power document understanding and enterprise knowledge retrieval at scale. They will architect and implement distributed backend systems that ingest, parse, and process complex documents while ensuring high availability and performance. This role involves building the foundational capabilities for retrieval-augmented generation and context grounding that enable autonomous AI agents. The engineer will translate product requirements into robust software solutions that turn advanced AI research into reliable customer features. They will take end-to-end ownership of features from initial design through deployment and ongoing optimization in production. Collaboration will be essential as they work alongside data scientists, product managers, and engineers to align technical execution with business goals. The role requires a passion for shipping high-quality software that solves real-world problems for enterprise customers.

Key facts

What you'll do

Design and develop scalable backend services that form the backbone of Intelligent Document Processing and Context Grounding platforms.

Implement document ingestion pipelines capable of handling diverse file formats and enterprise-scale content volumes with robust parsing and extraction logic.

Construct chunking strategies and embedding workflows that prepare complex documents for efficient semantic search and retrieval.

Build and optimize search and retrieval systems that power accurate knowledge access and contextual information discovery.

Develop and operate knowledge management services that ensure data integrity, security, and efficient lifecycle management.

Create resilient API layers that expose document intelligence capabilities to internal and external consumers with strong performance characteristics.

Orchestrate AI workflows that coordinate multiple services to deliver coherent, accurate outcomes through RAG and agentic patterns.

Establish evaluation pipelines that measure system quality, accuracy, and operational health to drive continuous improvement.

Architect cloud-native solutions on Azure, AWS, or GCP that balance scalability, latency, security, and operational excellence.

Implement event-driven architectures using messaging, caching, and databases to support high-throughput document processing workloads.

Leverage vector search technologies and semantic methods to enable powerful retrieval capabilities across large document collections.

Integrate LLMs and AI components to build production features that solve customer problems rather than experimental prototypes.

Partner with cross-functional teams including product managers, applied scientists, and designers to define and deliver software solutions.

Participate actively in architecture discussions, code reviews, and design reviews to elevate engineering standards across the organization.

Requirements

Bring 6 or more years of professional software engineering experience focused on building reliable production systems.

Demonstrate strong backend engineering skills with proven ability to design and implement distributed systems that operate at scale.

Show hands-on production experience with Python and/or C# to build maintainable and performant services.

Exhibit deep understanding of distributed systems principles including concurrency, networking, and robust software architecture patterns.

Have experience designing and implementing scalable APIs and microservices that meet strict reliability and performance requirements.

Possess practical experience building cloud-native applications on major platforms such as Azure, AWS, or GCP.

Display excellent debugging and problem-solving capabilities when facing complex, ambiguous technical challenges.

Demonstrate strong ownership by successfully delivering features from initial design through production operation and optimization.

Engage effectively in collaborative environments by communicating technical ideas clearly and constructively with diverse stakeholders.

Apply strong analytical skills to evaluate systems, diagnose issues, and implement resilient solutions that support enterprise workloads.

Nice to have

Experience in generative AI, retrieval-augmented generation, and LLM-powered application development.

Background with semantic search, vector databases, and intelligent document processing technologies.

Knowledge of OCR systems, search infrastructure, and knowledge management platforms that serve enterprise needs.

Familiarity with building and operating AI services that require high levels of security, compliance, and operational rigor.

Practical notes

This role operates in Bellevue.

Engagement is full time.

Candidates should be prepared for an iterative development process in a fast-moving growth environment.