Senior​/Lead Forward Deployed AI Engineer​/Anthropic – Data Intelligence-US East

Uses Anthropic/Claude and LLM integrations, focused heavily on RAG, vector search, and building agentic AI — hands-on AI dev work with enterprise data.

Senior/Lead Forward Deployed AI Engineer focused on Data Intelligence, designing and delivering enterprise AI solutions that connect Claude and other LLMs to Service Now and enterprise data. The role combines hands-on engineering of data pipelines, RAG/semantic search, LLM integrations, and client-facing consulting to move pilots into secure, production-ready deployments.

New Rocket is hiring a hands-on, client-facing Forward Deployed AI Engineer (Senior/Lead) for Data Intelligence to design, build, test, and deploy enterprise AI solutions grounded in governed enterprise data. The role sits at the intersection of AI engineering, data engineering, enterprise integration, and consulting, focusing on trustworthy data foundations and production-ready LLM applications (Claude and other approved models).

• Partner with client business, data, technology, security, and Service Now stakeholders to identify high-value use cases.
• Translate requirements into technical designs, prototypes, and production implementations.
• Build AI-enabled applications and workflows for knowledge discovery, service operations, document intelligence, decision support, and automation.
• Develop reusable Data Intelligence components, accelerators, integration patterns, and playbooks.
• Support full solution lifecycle: discovery, PoC, implementation, testing, rollout, monitoring, and continuous improvement.
• Communicate technical tradeoffs, risks, and recommendations to technical and non-technical stakeholders.

• Design and implement pipelines to ingest, transform, enrich, index, and retrieve structured and unstructured data.
• Connect AI solutions to Service Now, knowledge bases, document repositories, collaboration platforms, databases, data warehouses, lakes, and third-party SaaS.
• Support data profiling, quality assessment, schema mapping, metadata enrichment, classification, normalization, deduplication, and lineage.
• Define data access, retention, privacy, security, and usage controls with governance teams.
• Build integrations using APIs, SQL, ETL/ELT tools, event-driven patterns, middleware, and custom services.

• Design, build, and optimize retrieval-augmented generation (RAG) solutions using Claude and other LLMs.
• Implement document processing, chunking, metadata enrichment, embeddings, indexing, vector storage, hybrid retrieval, reranking, and source attribution.
• Configure and evaluate vector databases, search platforms, relational databases, and knowledge repositories.
• Build access-aware retrieval patterns respecting source permissions and implement retrieval tuning, citation, grounding, and feedback loops.

• Build and deploy LLM-powered applications using Claude, the Anthropic API, and other approved providers.
• Develop prompt and context engineering, structured outputs, tool use/function calling, orchestration, and error handling.
• Build agentic AI workflows with bounded tool access, human-in-the-loop controls, and validation/escalation paths.
• Support secure patterns such as Model Context Protocol (MCP) for connecting AI to authorized enterprise systems.

• Integrate AI and Data Intelligence capabilities with Service Now workflows, data, knowledge, APIs, and UX.
• Collaborate with Service Now architects and developers to meet security, scalability, and maintainability standards.

• Develop test plans, evaluation datasets, and QA processes for data-intensive AI solutions.
• Measure and improve performance across data quality, retrieval quality, model output quality, latency, reliability, adoption, and cost.
• Implement logging, tracing, monitoring, and feedback across pipelines, retrieval systems, model calls, and integrations.
• Contribute to LLMOps and Data Ops practices for reliable deployment and governance.

• Apply responsible-AI, security, privacy, and governance controls throughout design and deployment.
• Implement safeguards for sensitive data, prompt injection, unauthorized access, output validation, and audit logging.
• Work with security, governance, legal, compliance, and risk stakeholders to align with enterprise policies and regulations.

• Build trusted client and internal relationships and deliver one or more Data Intelligence/AI solutions from prototype to production readiness.
• Establish or improve secure data ingestion, retrieval, RAG, and enterprise integration capabilities for client engagements.
• Improve AI reliability via data preparation, access-aware retrieval, prompt/context engineering, testing, evaluation, and…