AI Engineer

Responsibilities

• Design, develop, test, and deploy the ISDP knowledge graph from the domain event store to production using cloud-native data pipelines.
• Model and evolve graph entities and relationships as new data sources are onboarded.
• Build and operate the MCP server exposing graph queries, event-store queries, and schema/DDL discovery to agent consumers.
• Define tool contracts, context, and guardrails for grounded and accurate agent responses.
• Ensure low-latency, secure, and cost-efficient serving for interactive and batch agent workloads.
• Own monitoring and observability for data freshness, pipeline health, query latency and cost, tool-call success rates, and answer quality.
• Instrument SLOs, dashboards, alerting, and tracing while driving incident response and reliability improvements.
• Partner with data engineers and application data source owners to ingest, validate, map, and troubleshoot industrial data.
• Establish data contracts, schema validation, quality checks, governance, cataloging, and lineage for the graph and its sources.

Requirements

• Bachelor's degree in Computer Science, Information Technology, or Engineering, or an equivalent combination of education and experience.
• At least 5 years of strong software engineering experience with Java and Python, including production-grade testing, CI/CD, and code quality practices.
• At least 3 years deploying data and AI systems to production on a GCP-native stack including Vertex AI, BigQuery, Dataflow or Apache Beam, Pub/Sub, Cloud Run or GKE, Cloud Storage, and Cloud Build or Artifact Registry.
• At least 3 years of graph data modeling and querying experience with property graphs and GQL or graph query patterns, such as BigQuery property graphs, Neo4j, or Spanner Graph.
• At least 3 years of hands-on Vertex AI experience involving agents, model serving, embeddings, and evaluation of agent answer quality.
• At least 2 years building LLM or agent systems involving tool use, RAG or grounding, and model API integration, with familiarity with MCP or comparable agent tool protocols.
• Expertise with Cloud Monitoring and Logging, OpenTelemetry, SLOs, dashboards, and alerting for data pipelines and services.
• At least 3 years of Infrastructure as Code experience with Terraform and secure-by-default engineering involving IAM, least privilege, and secrets management.
• Ability to work directly with data producers to model and validate industrial or enterprise data.
• Preferred qualifications include Dataplex or Data Catalog, streaming and CDC, event-driven or event-sourced architectures, user-facing graph applications and dashboards, relevant industrial systems exposure, data quality frameworks, schema evolution, and blue-green or zero-downtime data deployments.

Benefits

• Immediate medical, dental, vision, and prescription drug coverage.
• Flexible family care days, paid parental leave, new-parent ramp-up programs, subsidized backup childcare, adoption and surrogacy reimbursement, and fertility benefits.
• Vehicle discount programs for employees and family members and management leases.
• Tuition assistance and active employee resource groups.
• Paid time off for community service, paid holidays including the week between Christmas and New Year's Day, paid time off, and the option to purchase additional vacation time.
• Hybrid work arrangement requiring onsite attendance four or more days per week.
• Domestic relocation is not available for this position.