Enterprise Data Foundations

• Design and implement pipelines to ingest, transform, enrich, index, and retrieve structured and unstructured enterprise data.
• Connect AI solutions to approved enterprise data sources, including ServiceNow, knowledge bases, document repositories, collaboration platforms, databases, data warehouses, data lakes, and third-party SaaS systems.
• Support data profiling, data-quality assessment, schema mapping, metadata enrichment, classification, normalization, deduplication, and data lineage activities.
• Work with client data owners and governance teams to define appropriate data access, retention, privacy, security, and usage controls.
• Build data integration workflows using APIs, SQL, ETL/ELT tools, event-driven patterns, middleware, and custom services as appropriate.
• Help establish trusted-data patterns that ensure AI applications retrieve current, relevant, authorized, and contextually appropriate information.
• Identify data gaps, quality issues, duplicate content, stale information, and access-control problems that may reduce AI solution performance or user trust.

RAG, Search & Enterprise Knowledge Engineering

• Design, build, and optimize retrieval-augmented generation (RAG) solutions using Claude and other approved LLM technologies.
• Implement document-processing and knowledge-ingestion workflows, including parsing, chunking, metadata enrichment, embeddings, indexing, vector storage, hybrid retrieval, reranking, and source attribution.
• Develop semantic-search and enterprise knowledge experiences that help users discover, understand, summarize, and act on information.
• Configure and evaluate vector databases, search platforms, relational databases, and enterprise knowledge repositories appropriate to the client’s environment.
• Build access-aware retrieval patterns that respect source-system permissions and ensure users only receive information they are authorized to access.
• Improve answer quality and reliability through retrieval tuning, context management, source citation, grounding, relevance scoring, fallback behavior, and user feedback loops.
• Define and execute RAG evaluations measuring retrieval quality, context relevance, groundedness, completeness, accuracy, latency, cost, and user experience.

Claude, LLM & Agentic AI Development

• Build and deploy LLM-powered applications using Claude, the Anthropic API, and other approved model providers as appropriate.
• Develop prompt and context-engineering approaches that use clear instructions, structured inputs, examples, retrieval context, output schemas, and guardrails.
• Implement structured outputs, tool use/function calling, API integrations, workflow orchestration, and error-handling patterns for reliable AI applications.
• Build agentic AI workflows that can reason over approved data, access authorized tools, execute bounded tasks, and route exceptions to human reviewers.
• Define agent instructions, context strategies, tool permissions, validation logic, escalation paths, and human-in-the-loop controls.
• Support secure Model Context Protocol (MCP) or comparable patterns for connecting AI applications to authorized enterprise systems and tools.
• Evaluate AI and agentic workflow behavior for task completion, consistency, safety, accuracy, groundedness, latency, cost, and operational reliability.

ServiceNow & Enterprise Workflow Integration

• Integrate AI and Data Intelligence capabilities with ServiceNow workflows, data, knowledge, APIs, and user experiences.
• Collaborate with ServiceNow architects and developers to ensure AI solutions follow platform leading practices, security requirements, scalability expectations, and maintainability standards.
• Help clients embed AI insights and recommendations into the workflows where employees and customers already work.

Evaluation, Observability & Continuous Improvement

• Develop test plans, test cases, evaluation datasets, and quality-assurance processes for AI and data-intensive solutions.
• Measure and improve solution performance across data quality, retrieval quality, model output quality, task completion, latency, reliability, adoption, and cost.
• Implement logging, tracing, monitoring, and feedback mechanisms across data pipelines, retrieval systems, model calls, agent workflows, and integrations.
• Investigate production issues, identify root causes, document findings, and implement durable improvements.
• Support release-management practices, including version control for code, prompts, configuration, evaluation assets, data pipelines, and infrastructure.
• Contribute to LLMOps and DataOps practices that enable reliable deployment, testing, monitoring, governance, and ongoing optimization.

Responsible AI, Security & Governance

• Apply responsible-AI, security, privacy, and governance requirements throughout the design, development, testing, and deployment lifecycle.
• Implement safeguards for sensitive data, data leakage, unauthorized access, prompt injection, malicious content, unsafe tool use, and unintended agent behavior.
• Support controls such as access-aware retrieval, data masking, encryption, output validation, source attribution, approval workflows, audit logging, and confidence-based escalation.
• Work with client security, data governance, legal, compliance, and risk stakeholders to align solutions with enterprise policies and regulatory requirements.
• Document technical designs, data flows, security controls, model limitations, evaluation results, operating procedures, and known risks.

Collaboration, Innovation & Practice Development

• Work closely with AI Architects, AI Platform Engineers, data engineers, ServiceNow developers, product managers, designers, consultants, and client teams.
• Participate in discovery workshops, architecture sessions, sprint planning, backlog refinement, demos, code reviews, retrospectives, and executive readouts.
• Support client-facing technical research, demos, proofs of concept, implementation planning, and solution presentations.
• Contribute reusable code, Data Intelligence patterns, RAG components, evaluation assets, technical playbooks, and internal documentation.
• Stay current on Anthropic and Claude capabilities, enterprise AI trends, data platforms, RAG frameworks, semantic search, vector databases, agentic AI, and ServiceNow AI innovations.
• Identify opportunities to improve NewRocket’s Data Intelligence offerings, AI Foundry accelerators, Agent Packs, and enterprise AI delivery methodology.

What Success Looks Like In The First 6 Months

• Build trusted relationships with client stakeholders and NewRocket AI Foundry delivery teams.
• Deliver one or more high-quality, client-facing Data Intelligence or AI solutions from prototype through production-ready implementation.
• Establish or enhance secure data-ingestion, retrieval, RAG, and enterprise integration capabilities for assigned client engagements.