Software Engineer III - Applied AI Software

Software Engineer III - Applied AI Lead the architecture and delivery of enterprise AI-powered search and retrieval systems

Location:

Seattle

Compensation: $164, USD / year

At Blue Origin, we envision millions of people living and working in space for the benefit of Earth. We're working to develop reusable, safe, and low-cost space vehicles and systems within a culture of safety, collaboration, and inclusion. Join our team of problem solvers as we add new chapters to the history of spaceflight!

This role is part of Enterprise Technology (ET), where we're developing the digital infrastructure needed to build the road to space, with an emphasis on digital capabilities required to advance Blue Origin's mission. Enterprise Technology is the center of excellence for digital technology at Blue Origin, providing oversight and governance to align technology and business strategies.

We are seeking a skilled and self-directed Software Engineer III - Applied AI to join our enterprise search and AI team. You'll take meaningful ownership over the architecture and delivery of agentic, workflow-driven search and discovery platforms - powering enterprise knowledge graphs and AI-assisted retrieval systems that help Blue Origin teams find critical data in seconds.

At this level, you will drive technical decisions, mentor junior engineers, lead cross-functional delivery, and bring rigor to the areas that matter most: retrieval quality, LLM evaluation, frontend engineering depth, and system observability. You will help mature the team's standards in these areas and set the example for how we build production-grade AI applications.

• Lead full-stack development of search, RAG (Retrieval-Augmented Generation), and agentic AI applications using Python, Type Script/React, and Java
• Own retrieval pipeline quality: design and maintain evaluation harnesses for chunking strategies, embedding models, reranking, and end-to-end RAG response quality; drive improvements through offline and online evals
• Build and maintain LLM evaluation frameworks - including automated regression suites, human preference datasets, and task-specific benchmarks - to ensure consistent, trustworthy AI output
• Architect and deliver production-grade React frontends with deep component design, accessible UI patterns, state management (Redux, Zustand, or equivalent), and performance profiling
• Establish observability standards for AI systems: distributed tracing, structured logging, LLM-specific metrics (latency, token cost, hallucination rate, retrieval relevance), dashboards, and alerting
• Design and operate AWS-based infrastructure (ECS/EKS, Lambda, Open Search, S3, Cloud Watch) using Infrastructure as Code (Terraform/CDK); champion Dev Ops practices including CI/CD, automated testing gates, and release management
• Collaborate with other engineers to integrate embedding models, vector databases, and reranking systems into production-ready pipelines
• Mentor junior engineers in engineering craft, testing discipline, and AI product quality
• Partner with product, design, and mission stakeholders to translate complex requirements into durable technical solutions
• Contribute to engineering standards, ADRs, and team knowledge bases

• Bachelor's degree in Computer Science, Software Engineering, or a related field
• 5+ years of software engineering experience, with demonstrated ownership of production systems
• Fluent with LLMs as a development tool - spec-driven development, and building AI-first features
• Hands-on experience building and maintaining LLM/RAG pipelines (from embedding and retrieval through reranking and prompt design) and evaluation frameworks (offline evals, regression testing, relevance scoring, hallucination detection)
• Strong frontend engineering skills:
  React (hooks, context, custom component libraries), Type Script, state management, accessibility, and performance optimization
• Solid backend development in Python and/or Java; REST and Graph
  
  QL API design
• Experience with observability tooling: structured logging, distributed tracing (Open Telemetry, X-Ray, or equivalent), metrics dashboards (Cloud Watch, Datadog, Grafana), and alerting
• AWS cloud experience: ECS/EKS, Lambda, S3, Open Search, Cloud Watch, IAM
• Familiarity with Infrastructure as Code (Terraform, CDK, or Cloud Formation)
• Strong CI/CD practices: automated test gates, deployment pipelines, rollback strategies
• Excellent communication and cross-functional collaboration skills; ability to represent engineering decisions to non-technical stakeholders

• Experience with enterprise search platforms (Sinequa, Elasticsearch, Open Search)
• Knowledge graph or graph database experience (Neo4j, Amazon Neptune)
• AWS certification (Solutions Architect, Developer, or Machine Learning Specialty)
• Experience with agentic AI frameworks (Lang Chain, Llama Index, Auto Gen, CrewAI)
• Background in AI system reliability engineering
• Familiarity with data visualization (D3.js, Plotly,…