Overview: We are seeking an AI Platform Engineer to design and build the infrastructure that enables AI agents to operate securely, reliably, and at enterprise scale. This role focuses on developing the platform controls, governance mechanisms, integrations, and operational capabilities that support production AI systems. The ideal candidate is comfortable working across backend engineering, cloud infrastructure, AI/ML systems, security, and workflow orchestration in a greenfield environment.
Requirements:
- 5+ years of experience in platform, infrastructure, backend, or software engineering.
- Experience building or supporting production AI/ML, automation, workflow, or data-intensive systems.
- Hands-on experience with policy enforcement, authorization, audit logging, workflow orchestration, or enterprise integrations.
- Experience with identity and authentication technologies such as OAuth, OIDC, SAML, Entra ID, LDAP, or SPIFFE/SPIRE.
- Familiarity with durable workflow orchestration frameworks such as Temporal or similar technologies.
- Experience integrating APIs, message queues, middleware, enterprise applications, or legacy systems.
- Strong understanding of observability, distributed tracing, structured logging, and monitoring.
- Experience with infrastructure-as-code and deployment automation.
- Experience with AWS, Azure, or Google Cloud.
- Experience with Docker, Kubernetes, or comparable container platforms.
- Strong programming skills in Python, Java, Go, TypeScript, or a similar language.
- Ability to work from architectural specifications and build greenfield systems.
- Bachelor’s degree in computer science, engineering, information systems, or a related field, or equivalent practical experience.
- Experience with AI agents, large language models, prompt engineering, RAG, or multi-agent systems is preferred.
- Familiarity with Amazon Bedrock or another managed AI platform is preferred.
- Experience with OPA, Cedar, OpenTelemetry, Terraform, compliance frameworks, or regulated environments is a plus.
Responsibilities:
- Design control-plane infrastructure that separates agent proposal, decision, and execution.
- Build policy, guardrail, risk-scoring, and business-rule engines.
- Implement approval, versioning, configuration-governance, and rollback workflows.
- Develop access-control and policy-enforcement layers.
- Build governed connectors to enterprise applications and systems of record.
- Implement retry, timeout, staging, circuit-breaker, and failure-recovery patterns.
- Create tamper-resistant audit logging and compliance evidence capabilities.
- Build identity and workload-authentication services for AI agents.
- Implement observability using metrics, structured logging, tracing, and distributed telemetry.
- Develop synthetic-data environments, regression suites, scenario harnesses, and validation agents.
- Support agent onboarding and maintain stable integration contracts.
- Provision and deploy services using containers, infrastructure-as-code, and CI/CD.
- Collaborate with architects, engineers, security teams, and business stakeholders.
- Build and support production AI agents, tools, and workflows.