AI/ML engineer II

Blue Origin • Cupertino, CA

2d

About The Position

Blue Origin Operations is building AI-powered operational tooling that transforms fragmented telemetry, documentation, and runbooks into fast, trustworthy answers for engineers operating its systems. The AI/ML Engineer will design, build, and operate agentic workflows that detect incidents, investigate root causes, and guide engineers toward resolution across edge-to-cloud production systems. The role partners with platform, operations, software, and domain teams to define agent capabilities; build the tools and knowledge layers behind them; and move solutions from prototype through audited production deployment. The work aims to reduce incident investigation time and enable self-service debugging for on-floor technicians and engineers.

The position is part of Blue Origin Operations, which includes Integrated Supply Chain, Test Operations, Safety, Quality, and Mission Assurance, and provides manufacturing and supply-chain support across Blue Origin facilities.

Requirements

• Bachelor's degree in Computer Science, Electrical Engineering, or a related field.
• At least 2 years of software or ML engineering experience, including experience with production systems.
• Hands-on experience building LLM-based applications, including prompt engineering, tool use or function calling, and retrieval-augmented generation (RAG).
• Experience with AWS services such as Lambda, S3, DynamoDB, CloudWatch, and IAM.
• Python programming skills and experience building APIs and services.
• Experience with infrastructure as code, such as AWS CDK, CloudFormation, or Terraform.
• Familiarity with observability concepts, including logs, metrics, traces, alerting, and incident response.
• Ability to write clear design documents, interface definitions, and operational documentation.

Nice To Haves

• Experience designing multi-agent orchestration patterns and agent-to-agent communication.
• Experience with OpenSearch or other vector and hybrid search systems.
• Experience building evaluation harnesses for LLM and agent systems, including offline benchmarks and LLM-as-judge methods.

Responsibilities

• Design and build multi-agent systems for incident triage and root cause analysis, including specialized log-analysis, metrics-analysis, and root-cause-analysis agents coordinated by a central orchestrator.
• Build and maintain knowledge bases covering internal documentation, runbooks, and escalation paths, including ingestion pipelines, chunking and retrieval strategies, and relevance evaluation.
• Provision and manage AI infrastructure as code with AWS CDK and create repeatable deployments across environments.
• Define evaluation frameworks and metrics for agent accuracy, hallucination rate, tool-call correctness, latency, and cost, and drive continuous improvement.
• Partner with engineers and domain teams to turn real incident patterns into new tools, agents, and knowledge content.
• Document agent architectures, tool interfaces, guardrails, and operational runbooks for the AI assistant.

Benefits

• Medical, dental, and vision insurance.
• Basic and supplemental life insurance.
• Paid parental leave.
• Short- and long-term disability.
• 401(k) with company match of up to 5%.
• Education Support Program.
• Stock options for regular employees working at least 20 hours per week.
• Paid time off of up to four weeks per year, based on weekly scheduled hours.
• Up to 14 company-paid holidays.
• Depending on role type and job level, employees may be eligible for benefits and bonuses based on individual contributions and company results.

What This Job Offers

• Job Type: Full-time
• Career Level: Mid Level