AI Platform Engineer

Direct message the job poster from Semantic Enterprise AI Employee Experience Advocate | Shaping Positive Work Cultures | Trusted HR Advisor About the Role Semantic Enterprise AI (SEAI) builds next-generation Decision Engine workflows that integrate machine learning, agentic automation, and advanced reasoning tools into enterprise products that empower organizations to make better upside decisions faster. As AI Platform Engineer, you'll architect and build the complete platform infrastructure, from agent orchestration and workflow execution to enterprise security and observability. You'll own the full stack, including evaluating and implementing agent frameworks, designing cloud architecture, writing infrastructure-as-code, and building the evaluation systems that ensure reliable workflows at scale. This is a founding platform role where you'll make critical technical decisions, collaborate closely to integrate intelligent capabilities, and grow and lead the platform engineering team. What You'll Do Design and build a configuration-driven multi-agent platform that enables rapid workflow deployment through declarative configurations rather than code changes and that supports multiple intelligence levels with state management and distributed coordination. Architect and implement the agent orchestration infrastructure; evaluate and integrate frameworks and compute platforms to build production-grade agent execution at scale. Own the complete infrastructure stack including cloud architecture design, infrastructure-as-code, CI/CD pipelines, and deployment systems. Build enterprise-grade capabilities for multi-tenant data isolation, agent-to-agent authentication, security controls, audit trails, and production compliance frameworks. Design evaluation and observability systems that include rule-based validation, LLM-as-judge frameworks, metrics tracking, and full execution visibility for workflow reliability and performance optimization. Create tool integration frameworks and collaborate with ML Engineers to define service contracts, API patterns, and integration standards that enable agents to reliably consume ML models, external APIs, and data services with robust error handling. Required Qualifications Bachelor's or Master's degree in Computer Science, Distributed Systems, or related technical field (or equivalent practical experience). 5-7 years of experience building production distributed systems, with at least 2+ years working with LLMs, agent frameworks, or AI orchestration systems. Deep expertise in Python and production system design, with experience building scalable backend services and distributed workflows. Hands‑on experience with agent frameworks or workflow orchestration systems such as LangChain, LlamaIndex, CrewAI, Temporal, Prefect, Airflow, or similar technologies. Production cloud infrastructure experience (AWS, GCP, or Azure) including compute orchestration (Lambda, Kubernetes, container services), and proven ability to architect for scale, reliability, and security. Infrastructure‑as‑Code proficiency. Demonstrated ability to write and maintain Terraform, AWS CDK, CloudFormation, or similar IaC tools to manage production infrastructure. Multi‑tenant system design experience. Understanding of data isolation, security boundaries, and enterprise SaaS architecture patterns. Strong system design and architecture skills: ability to design configuration‑driven systems, state management, workflow engines, and distributed agent coordination. Experience with platform observability and monitoring. Experience building logging, tracing, metrics monitoring, and alerting systems for distributed applications (DataDog, CloudWatch, Prometheus, or similar). Proficiency with CI/CD practices, containerization (Docker, Kubernetes), API design, and modern software development practices. Preferred Qualifications Experience building multi‑agent frameworks, deploying LLMs at scale, managing prompt orchestration, and optimizing inference costs and fallback strategies. Background with state machines, event‑driven architectures, distributed task queues, workflow DAGs, or automated testing for AI agent behaviors. Knowledge of multi‑tenant security, encryption, PII detection, data security frameworks, or AI safety guardrails for enterprise production systems. Track record building internal platforms, SDKs, configuration systems, or developer tools that enable other engineers to build on your infrastructure. Experience mentoring engineers, leading architecture decisions, contributing to open‑source projects (agent/workflow/LLM frameworks), or relevant cloud certifications (AWS Solutions Architect, DevOps Engineer). We value diverse perspectives and encourage all qualified candidates to apply, even if you don't match every qualification perfectly. We are currently seeking candidates who are legally authorized to work in the United States or Canada. Preference will be given to applicants located in Washington, Oregon, or British Columbia. We are committed to providing equal employment opportunities and do not discriminate based on race, color, religion, sex, national origin, age, disability, or genetic information. Salary Range: Up to $140,000 USD (US) / $140,000 CAD (Canada), depending on experience and location. #J-18808-Ljbffr