Principal Software Engineer – Data & AI
About the role
and include the company vision and role summary. We need to include sections only when posting has real specific content. Must include Responsibilities, Must-Haves (maybe as Requirements), Preferred (maybe as Qualifications or Skills), Benefits, Pay. Schedule not present, so omit. We must not repeat job title as heading. No Job ID. We must use- for any list of duties/requirements/benefits. Use
for prose. We need to preserve all substantive information; do not invent or summarize away detail. We need to remove boilerplate: Application Close Date line, Culture Statement? Might keep but it's not boilerplate; but it's somewhat generic. I'd keep it as part of About the role maybe. Also remove Export Control Regulations, Background Check, Equal Employment Opportunity, Affirmative Action etc. Those are legal boilerplate. Remove them. Also remove "Other Site Ranges May Differ". That's part of Pay but we can keep base pay range. We need to include Base Pay Range For WA applicants is $230,773.00 - $323,081.85. That's pay. Benefits section: list benefits. We need to ensure we don't include filler like "commensurate with experience". Not present. Let's extract content: - Company vision: "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!" - Role summary: "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. Role Summary We are looking for a Principal Software Engineer to set the technical direction for how Blue Origin finds, reasons over, and acts on its enterprise knowledge. As a senior individual contributor, you'll own the architecture of our agentic AI platform - the lakehouse, knowledge graph, retrieval systems, and natural-language interfaces that help engineering, manufacturing, and mission teams find critical data in seconds, not days. You'll lead through technical credibility, not reporting authority - staying hands-on, writing production code, and proving out the hard parts yourself. Your impact is enterprise-wide. Your work reaches engineers designing engines, technicians building vehicles, quality teams investigating anomalies, and mission teams in flight, and is increasingly reused by other products through shared APIs and MCPs." We can combine. Responsibilities list: - Own the architecture and roadmap for Blue Origin's agentic AI, retrieval, and semantic reasoning platform. - Stay hands-on across the full stack - write production code, build reference implementations, and prove out the hard parts yourself rather than delegating and reviewing. - Design shared capabilities for reuse - exposed through documented APIs and MCPs - so other teams and products adopt them instead of rebuilding data and AI foundations. - Set architecture direction across the platform portfolio (ingestion, knowledge graph, enterprise search, natural-language-to-SQL, multi-modal evidence), establishing reusable patterns and CI/CD, IaC, and release standards. - Mentor senior / mid-level engineers and steward the standards, ADRs, and reference implementations that raise the whole team's bar. - Establish AI evaluation and observability as engineering disciplines: regression suites, accuracy thresholds, and release gates, plus tracing and metrics (latency, cost, hallucination rate, relevance) on every production surface. - Make AI output defensible - set the standard that answers trace to source-grounded evidence with provenance, access control, and confidence, and drive retrieval and generation quality through offline and online evaluation. Must-Haves list: - 10+ years building production software, with 7+ years of cross-team architecture ownership or technical leadership. - Delivered production LLM, RAG, or agentic AI systems end to end - ingestion, retrieval, reranking, prompt and context design, serving. - Built and operated an enterprise data platform - a lakehouse or distributed architecture (Spark, Delta Lake, or equivalent), with a metadata-driven ingestion framework - including schema evolution, pipeline reliability, and workload cost. - Full-stack depth: production Python, REST/GraphQL API design, and AWS with Infrastructure as Code (Terraform or CDK) and mature CI/CD. - Passion for Blue Origin’s mission and ability to work in a fast-paced, dynamic environment. Preferred list: - Lakehouse platforms (Databricks, Spark, Delta Lake, Unity Catalog) - Knowledge graphs (Neo4j, Neptune) - Enterprise search (Sinequa, OpenSearch) - Natural-language-to-SQL - AI observability, inference cost and latency optimization - Multi-modal AI over documents, imagery, or telemetry - Graduate degree or published open-source work in applied AI Pay: Base Pay Range For WA applicants is $230,773.00 - $323,081.85 Benefits list: - Medical, dental, vision, basic and supplemental life insurance, paid parental leave, short and long-term disability, 401(k) with a company match of up to 5%, and an Education Support Program. - Stock Options for all regular employees (working at least 20 hours/week) - Paid Time Off: Up to four (4) weeks per year based on weekly scheduled hours, and up to 14 company-paid holidays. - Dependent on role type and job level, employees may be eligible for benefits and bonuses based on the company's intent to reward individual contributions and enable them to share in the company's results, or other factors at the company's sole discretion. Bonus amounts and eligibility are not guaranteed and subject to change and cancellation. Please check with your recruiter for more details. We might keep that last sentence as prose. We should not include "Please check with your recruiter for more details." That's application instruction? It's about benefits details; maybe keep but it's not instruction to apply. Could keep. We must not include "Other Site Ranges May Differ". We'll omit. Now produce HTML:
About the role
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 looking for a Principal Software Engineer to set the technical direction for how Blue Origin finds, reasons over, and acts on its enterprise knowledge. As a senior individual contributor, you'll own the architecture of our agentic AI platform - the lakehouse, knowledge graph, retrieval systems, and natural-language interfaces that help engineering, manufacturing, and mission teams find critical data in seconds, not days. You'll lead through technical credibility, not reporting authority - staying hands-on, writing production code, and proving out the hard parts yourself. Your impact is enterprise-wide. Your work reaches engineers designing engines, technicians building vehicles, quality teams investigating anomalies, and mission teams in flight, and is increasingly reused by other products through shared APIs and MCPs.
Responsibilities
- Own the architecture and roadmap for Blue Origin's agentic AI, retrieval, and semantic reasoning platform.
- Stay hands-on across the full stack - write production code, build reference implementations, and prove out the hard parts yourself rather than delegating and reviewing.
- Design shared capabilities for reuse - exposed through documented APIs and MCPs - so other teams and products adopt them instead of rebuilding data and AI foundations.
- Set architecture direction across the platform portfolio (ingestion, knowledge graph, enterprise search, natural-language-to-SQL, multi-modal evidence), establishing reusable patterns and CI/CD, IaC, and release standards.
- Mentor senior / mid-level engineers and steward the standards, ADRs, and reference implementations that raise the whole team's bar.
- Establish AI evaluation and observability as engineering disciplines: regression suites, accuracy thresholds, and release gates, plus tracing and metrics (latency, cost, hallucination rate, relevance) on every production surface.
- Make AI output defensible - set the standard that answers trace to source-grounded evidence with provenance, access control, and confidence, and drive retrieval and generation quality through offline and online evaluation.
Requirements
- 10+ years building production software, with 7+ years of cross-team architecture ownership or technical leadership.
- Delivered production LLM, RAG, or agentic AI systems end to end - ingestion, retrieval, reranking, prompt and context design, serving.
- Built and operated an enterprise data platform - a lakehouse or distributed architecture (Spark, Delta Lake, or equivalent), with a metadata-driven ingestion framework - including schema evolution, pipeline reliability, and workload cost.
- Full-stack depth: production Python, REST/GraphQL API design, and AWS with Infrastructure as Code (Terraform or CDK) and mature CI/CD.
- Passion for Blue Origin’s mission and ability to work in a fast-paced, dynamic environment.
Preferred Qualifications
- Lakehouse platforms (Databricks, Spark, Delta Lake, Unity Catalog)
- Knowledge graphs (Neo4j, Neptune)
- Enterprise search (Sinequa, OpenSearch)
- Natural-language-to-SQL
- AI observability, inference cost and latency optimization
- Multi-modal AI over documents, imagery, or telemetry
- Graduate degree or published open-source work in applied AI
Pay
Base Pay Range For WA applicants is $230,773.00 - $323,081.85
Benefits
- Medical, dental, vision, basic and supplemental life insurance, paid parental leave, short and long-term disability, 401(k) with a company match of up to 5%, and an Education Support Program.
- Stock Options for all regular employees (working at least 20 hours/week)
- Paid Time Off: Up to four (4) weeks per year based on weekly scheduled hours, and up