AI Application Architect
Procore Technologies2 hours ago
Base Salary
$233k - $321k/yr
Responsibilities
- Define architecture for AI-native applications, including agentic systems, RAG pipelines, multi-model inference layers, and human-in-the-loop workflows.
- Drive infrastructure decisions for scalable AI workloads, vector databases, workflow orchestration, and asynchronous compute.
- Design and govern integrations between LLMs and backend services, including prompt management, context optimization, and cost governance.
- Lead LLMOps and observability strategy covering tracing, evaluation pipelines, prompt versioning, and drift detection.
- Establish security and compliance practices for AI systems, including injection hardening, guardrails, data residency, and model supply-chain security.
- Partner with product and research teams to evaluate and adopt emerging AI capabilities such as reasoning models, multimodal systems, fine-tuning, and RLHF.
- Champion API design, schema governance, testing strategies, and architecture decision records.
- Mentor senior engineers and establish technical communities around AI platform topics.
Requirements
- 10+ years of software engineering experience and 5+ years in a principal, staff, or architect-level role.
- Hands-on experience designing and shipping production LLM-powered applications, not only prototypes.
- Experience shipping complex user-facing application platforms, particularly SaaS, productivity, or enterprise software.
- Ability to lead full-stack teams building rich web application experiences with React, TypeScript/Node.js, modern frontend architectures, Python, and strong API design.
- Deep understanding of user management, RBAC/ABAC permissions, audit logging, compliance frameworks, multi-tenant governance, and administrative tooling.
- Experience building contextual or adaptive user experiences based on user state, workflow context, or personalization signals.
- Strong grasp of cloud-native architecture and container security on AWS, GCP, or Azure, including Kubernetes, Helm, and CI/CD.
- Strong understanding of API security, including OAuth2, CSRF, rate limiting, secrets management, and zero-trust principles for AI endpoints.
- Preferred experience with MCP or comparable tool-calling and plugin infrastructure.
- Preferred familiarity with Temporal or Prefect for long-running AI workflows and LLM evaluation frameworks such as automated judging, red-teaming, and regression suites.
- Preferred background in developer-facing products, internal AI platforms, or AI coding tooling, plus understanding of ML model supply-chain security.
- Open-source AI tooling contributions or published architectural writing are preferred.