AI Engineer

Role: AI Engineer

Location: Remote (NJ)

Type: Contract

• We are seeking an experienced AI Engineer / Diamond Layer Tech Lead to lead the design and development of advanced AI agent platforms, semantic retrieval solutions, knowledge graphs, and data foundations. This role requires a hands-on technical leader with strong expertise in Python, Agentic AI, RAG, knowledge graphs, GCP, BigQuery, and AI evaluation/observability.
• The Tech Lead will own the orchestration, semantic, and data-foundation architecture while developing reusable agent patterns, mentoring engineers, and driving solutions toward production readiness.

Key Responsibilities:

AI Agent & Backend Engineering

• Design and develop advanced AI agent services using Python.
• Build multi-step agent workflows, orchestration state management, and tool invocation frameworks.
• Develop reusable agent patterns, fallback mechanisms, and multi-agent execution workflows.
• Implement deterministic and LLM-assisted routing across multiple domains.
• Design standard contracts for agents, tools, and model/platform adapters.
• Develop agent registration and multi-domain execution capabilities.

RAG & AI Retrieval

• Design and implement advanced Retrieval-Augmented Generation (RAG) solutions.
• Develop retrieval, reranking, grounding, and context-assembly strategies.
• Improve answer accuracy and reduce hallucinations through effective retrieval and grounding techniques.
• Support citation, source attribution, and cross-domain synthesis.
• Design retrieval solutions that provide reliable and traceable answers from enterprise data.

Knowledge Graph & Semantic Engineering

• Design and develop enterprise knowledge-graph solutions using:
• RDF
• SPARQL
• Ontology Modeling
• SHACL
• Stardog
• Virtual Graphs
• Develop relational-to-semantic data mappings.
• Manage semantic versioning and graph promotion processes.
• Establish semantic models that support AI agents, retrieval, and cross-domain data discovery.
• 4. Data Engineering & Data Foundations
• Work extensively with SQL and Google BigQuery.
• Perform source discovery and data-gap analysis.
• Develop and maintain data dictionaries and business-key validation processes.
• Perform data reconciliation and source-of-truth assessments.
• Evaluate data quality, freshness, lineage, and completeness.
• Build reliable data foundations supporting AI agents and semantic platforms.
• 5. Cloud & Infrastructure
• Design and deploy AI agent services within Google Cloud Platform (GCP).
• Work with:
• GKE
• BigQuery
• Google Cloud Storage (GCS)
• Support agent-runtime deployment and semantic-platform connectivity.
• Configure secure service identities and environment-specific deployments.
• Ensure scalable and secure infrastructure for production AI workloads.
• 6. CI/CD & Release Engineering
• Establish CI/CD pipelines for AI agents and knowledge-graph components.
• Implement automated evaluation gates as part of the release process.
• Manage versioning for:
• Prompts
• Tools
• Data mappings
• Ontologies
• Queries
• Deployment configurations
• Promote tested AI and semantic components across environments.
• 7. AI Testing & Evaluation
• Establish evaluation frameworks for AI agents based on:
• Accuracy
• Relevance
• Groundedness
• Completeness
• Hallucination rate
• Latency
• Cost
• Develop benchmark scenarios and gold-answer datasets.
• Implement automated evaluation processes to validate agent quality before production releases.
• 8. Observability & Operations
• Implement end-to-end tracing across:
• Master coordinator
• Domain agents
• Tools
• Semantic layer
• Data layer
• Use Langfuse or equivalent LLM observability platforms.
• Develop operational dashboards and reporting using Grafana.
• Monitor model performance, agent behavior, latency, usage, and cost.
• Support model comparison and continuous optimization.
• 9. Security & Governance
• Implement identity-aware retrieval and least-privilege data access.
• Establish cross-domain security guardrails.
• Protect prompts, traces, and sensitive data throughout the agent lifecycle.
• Ensure source attribution and complete auditability of AI-generated responses and agent activities.
• Support secure and governed access to enterprise data and semantic resources.
• Tech Lead Responsibilities
• Own the technical design for AI orchestration, semantic architecture, and data foundations.
• Remain hands-on with architecture, coding, integration, and troubleshooting.
• Define reusable patterns and engineering standards for AI agents and semantic solutions.
• Mentor engineers and provide technical guidance across the development team.
• Drive technical decisions related to agent architecture, retrieval, knowledge graphs, and data platforms.
• Establish engineering practices for evaluation, observability, security, and production readiness.
• Collaborate with engineering and business stakeholders to translate requirements into scalable AI solutions.
• Lead solutions from architecture and development through testing, deployment, and production support.