Job Summary:
Seeking an AI Engineer / Technical Lead with deep expertise in Agentic AI, Retrieval-Augmented Generation (RAG), semantic retrieval, knowledge graphs, data foundations, and agent quality. The role will focus on designing and implementing a Master Coordinator, domain agents, orchestration workflows, semantic retrieval capabilities, and knowledge graph integrations. The engineer will remain hands-on while owning orchestration, semantic, and data-foundation architecture, establishing reusable engineering patterns, mentoring engineers, and driving AI evaluation and production readiness.
Key Responsibilities:
• Design and implement Master Coordinator and domain-agent architectures using advanced Python, multi-step workflows, orchestration state, tool invocation, and fallback handling.
• Develop reusable agent patterns and establish standardized approaches for agent services, orchestration, and workflow execution.
• Implement standard agent and tool contracts, agent registration, deterministic and LLM-assisted routing, multi-domain execution, and model/platform adapters.
• Design and implement advanced SQL and BigQuery solutions for source discovery, data-gap analysis, data dictionaries, business-key validation, reconciliation, and source-of-truth assessment.
• Establish data quality, freshness, lineage, and data-source validation practices across enterprise data foundations.
• Design and implement advanced RAG capabilities, including retrieval, reranking, grounding, prompt and context assembly, citation support, and hallucination reduction.
• Enable cross-domain synthesis and reliable retrieval across enterprise data and knowledge sources.
• Design and implement knowledge graph solutions using RDF, SPARQL, ontology modeling, SHACL, Stardog, virtual graphs, and relational-to-semantic mappings.
• Manage semantic versioning and graph promotion processes across development and production environments.
• Design and deploy AI and semantic workloads on GCP using GKE, BigQuery, and GCS.
• Support agent-runtime deployment, semantic-platform connectivity, environment configuration, and secure service identities.
• Implement CI/CD pipelines for agents and knowledge graphs, including automated evaluation gates and versioning of prompts, tools, mappings, ontologies, queries, and deployment definitions.
• Develop comprehensive agent evaluation practices covering accuracy, relevance, groundedness, completeness, hallucination, latency, and cost.
• Establish benchmark scenarios and gold-answer datasets for consistent evaluation of AI solutions.
• Implement end-to-end tracing across coordinator, agent, tool, semantic, and data layers.
• Utilize Langfuse or equivalent LLM observability platforms and Grafana for reporting, monitoring, and model comparisons.
• Implement identity-aware retrieval, least-privilege data access, cross-domain guardrails, trace and prompt-data protection, source attribution, and complete auditability.
• Remain hands-on with development while conducting technical and design reviews.
• Create reusable engineering patterns, mentor engineers, and drive evaluation and production readiness.
Required Qualifications:
• Strong hands-on experience with Python and backend engineering for AI and agent-based applications.
• Advanced experience developing agent services, multi-step workflows, orchestration state, tool invocation, fallback handling, and reusable agent patterns.
• Strong experience with agent and tool contracts, agent registration, routing, multi-domain execution, and model/platform adapters.
• Advanced SQL and BigQuery experience, including source discovery, data-gap analysis, data dictionaries, business-key validation, reconciliation, and data-quality assessment.
• Deep hands-on experience with RAG, including retrieval, reranking, grounding, prompt/context assembly, citation support, hallucination reduction, and cross-domain synthesis.
• Strong experience with knowledge graph technologies, including RDF, SPARQL, ontology modeling, SHACL, Stardog, virtual graphs, and relational-to-semantic mappings.
• Experience with semantic versioning and knowledge graph promotion processes.
• Hands-on experience with GCP, GKE, BigQuery, and GCS in AI or data engineering environments.
• Experience deploying and configuring agent runtimes, semantic platforms, and secure service identities.
• Experience implementing CI/CD pipelines for AI agents and knowledge graph components.
• Experience versioning prompts, tools, mappings, ontologies, queries, and deployment definitions.
• Strong experience evaluating AI agents for accuracy, relevance, groundedness, completeness, hallucination, latency, and cost.
• Experience developing benchmark scenarios and gold-answer datasets for AI evaluation.
• Experience with end-to-end AI observability and tracing across agent, tool, semantic, and data layers.
• Experience with Langfuse or equivalent LLM observability platforms and Grafana.
• Strong understanding of identity-aware retrieval, least-privilege data access, guardrails, sensitive prompt/data protection, source attribution, and auditability.
• Strong technical leadership skills with the ability to remain hands-on, establish reusable patterns, mentor engineers, and drive production readiness.
