AI Platform Runtime Engineer

retrieval and tool execution-while maintaining reliability, cost control, security, and measurable quality over time. You will own the core runtime infrastructure that powers the NAVEX AI Product System, including intelligence primitives, cloud integration, release hardening, and CI/CD pipelines that ensure AI experiences are resilient, deterministic, and production ready. If you want to build the runtime backbone of a governed, enterprise-grade agentic AI platform, this role is for you.

You'll thrive in this hybrid role surrounded by an engaged, collaborative team deeply committed to your success. Join us and help shape what's next!

What you'll get:

• Meaningful Purpose. Your work helps organizations operate with integrity and protect their people-at a scale few companies can match.

• High-Performance Environment. We move with urgency, set ambitious goals, and expect excellence. You'll be trusted with real ownership and supported to do the best work of your career.

• Candid, Supportive Culture. We communicate openly, challenge ideas-not people-and value teammates who embrace bold thinking and continuous improvement.

• Growth That Matters. You can count on authentic feedback, strong accountability, and leaders invested in your success so you can achieve real growth.

• Rewards for Results. We provide clear, competitive compensation designed to recognize measurable outcomes and real impact.

What you'll do:

• Implement agent orchestration and multi-agent workflows-develop orchestration logic, including agent-to-agent communication patterns where needed

• Build retrieval and grounding components-implement RAG pipelines and continuously evaluating and iterating to improve quality

• Build and maintain core AI platform primitives (orchestration, context, memory boundaries, configuration layers)

• Integrate and optimize AWS Bedrock as the managed execution substrate

• Design and implement deterministic AI release bundles with versioned prompt and orchestration artifacts; build rollback mechanisms, tenant-level feature flags and controlled rollout infrastructure

• Implement tenant isolation, session boundaries, and memory scoping across AI runtime

• Build and maintain CI/CD pipelines for AI artifacts deployment and validation

• Instrument agent observability and runtime monitoring-establish end-to-end tracing for agent runs, failure analysis, and latency and cost monitoring

• Operationalize safe deployment practices

• Implement security controls for tool-using agents-apply strict output validation and secure tool integration practices to mitigate common LLM risks and protect user and customer data

• Build dashboards, alerts, and cost guardrails for monitoring AI runtime health

• Collaborate with AI Architect and evaluation teams to ensure platform primitives support governance and quality gating requirements

What you'll bring:

• Bachelor's or Master's degree in Computer Science, Software Engineering, or a related field

• 5+ years' experience in platform engineering, infrastructure engineering, or backend systems development, with hands-on experience building production backend services, APIs, and distributed systems with a bias toward reliability and operability

• Demonstrated agentic build experience (work or serious personal projects)-some experience building or contributing to agentic or LLM-based systems, including prototypes moved to production

• Strong experience with AWS services, particularly Bedrock, Lambda, Step Functions, IAM, and related managed services

• Experience building and operating multi-tenant SaaS platforms at production scale

• Proficiency in Python and/or TypeScript/Node.js for backend service development

• Experience with CI/CD pipeline design and infrastructure-as-code tools (Terraform, CDK, or CloudFormation)

• Knowledge of containerization and orchestration (Docker, ECS, or Kubernetes)

• Understanding of AI/ML runtime requirements including model serving, context management, and memory systems

• Knowledge of non-deterministic system iteration loops-comfort working in an iterative "build, test, ship, observe, refine" cycle where agent behavior must be validated with systematic evaluation

• Experience with observability tooling, cost monitoring, and operational runbook development

• Culture Agility. Comfort working in a fast-paced, candid environment that values innovation, healthy debate, and follow-through

• Fuel performance and outcomes. Leverage your job competencies and champion NAVEX's core values

Our side of the deal:

• We'll be clear, we'll move fast, and we'll invest in your success. You deserve to be supported, challenged, and rewarded for the impact you make-and we commit to doing that every step of the way.
• The starting pay for this role is $155,000+ per annum with 15% MBO. Discover how you can grow, lead, and make an impact by visiting our career page to learn more. NAVEX is an equal opportunity employer committed to including individuals of all backgrounds, including those with disabilities and