Forward Deployed AI Engineer/Anthropic – Data Intelligence-Netherlands/Western E

Role

Forward Deployed AI Engineer — Data Intelligence responsible for designing, building, testing, and deploying enterprise AI solutions that connect Claude and other LLMs with ServiceNow, enterprise data, and business workflows. The role blends AI engineering, data engineering, enterprise integration, and client-facing consulting to move clients from pilots to secure, scalable production deployments.

Key Responsibilities

Data Intelligence & AI Solution Delivery

• Partner with client stakeholders to identify high-value AI and data use cases.
• Translate requirements into technical designs, prototypes, production implementations, and delivery plans.
• 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 the full lifecycle: discovery, data assessment, proof of concept, implementation, testing, rollout, monitoring, and improvement.

Enterprise Data Foundations

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

RAG, Search & Enterprise Knowledge Engineering

• Design, build, and optimize retrieval-augmented generation (RAG) solutions using Claude and other LLMs.
• Implement document processing, chunking, embeddings, indexing, vector storage, hybrid retrieval, reranking, and source attribution.
• Configure and evaluate vector databases, search platforms, relational databases, and enterprise knowledge repositories.
• Build access-aware retrieval patterns and improve answer quality through retrieval tuning, context management, citation, and feedback loops.
• Define and execute retrieval/RAG evaluations for quality, groundedness, latency, cost, and UX.

Claude, LLM & Agentic AI Development

• Build and deploy LLM applications using Claude, the Anthropic API, and other approved model providers.
• Develop prompt and context-engineering approaches with structured inputs, examples, retrieval context, output schemas, and guardrails.
• Implement structured outputs, tool use/function calling, workflow orchestration, validation, and error handling.
• Build agentic workflows with bounded tool access and human-in-the-loop controls; apply Model Context Protocol (MCP) or comparable patterns.

ServiceNow & Enterprise Workflow Integration

• Integrate AI and Data Intelligence capabilities with ServiceNow workflows, APIs, data, and user experiences.
• Collaborate with ServiceNow architects and developers to meet platform best practices, security, scalability, and maintainability.

Evaluation, Observability & Continuous Improvement

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

Responsible AI, Security & Governance

• Apply responsible-AI, security, privacy, and governance requirements across the lifecycle.
• Implement safeguards against data leakage, unauthorized access, prompt injection, unsafe tool use, and unintended agent behavior.
• Support controls like access-aware retrieval, data masking, encryption, output validation, audit logging, and confidence-based escalation.

Requirements

• 3+ years of relevant experience in software engineering, AI engineering, data engineering, analytics engineering, cloud engineering, systems integration, or related roles.
• Hands-on experience building applications, data pipelines, integrations, APIs, automations, or cloud services.
• Strong proficiency in Python; experience with JavaScript/TypeScript, Java, SQL, or similar languages is valuable.
• Experience with structured and unstructured data, relational databases, document repositories, APIs, and cloud storage.
• Experience with SQL, data transformation, data modeling, ETL/ELT, and data ingestion concepts.
• Exposure to generative AI, LLMs, RAG, embeddings, vector search, semantic search, prompt engineering, AI agents, or LLM APIs.
• Experience with REST APIs, JSON, OAuth, service accounts, and authentication/authorization patterns.
• Familiarity with cloud platforms such as AWS, Microsoft Azure, or Google Cloud Platform.
• Understanding of software-development best practices: Git, code review, testing, debugging, documentation, and agile delivery.
• Strong problem-solving, written and verbal communication skills, and the ability to work directly with clients.

Preferred Qualifications

• Experience with Claude, the Anthropic API, Anthropic Console, or related Anthropic tools and partner enablement.
• Experience designing or implementing RAG systems, embeddings, vector databases, hybrid search, and retrieval evaluation.
• Experience with vector DBs/search tools: Pinecone, Weaviate, pgvector, OpenSearch, Elasticsearch, Azure AI Search, Vertex AI Search.
• Experience with LLM frameworks: LangChain, LangGraph, LlamaIndex, Semantic Kernel, or equivalents.
• Experience with Model Context Protocol (MCP), agentic AI, tool use/function calling, and secure AI-to-system integrations.
• Experience with data platforms: Snowflake, Databricks, BigQuery, Redshift, PostgreSQL, MongoDB, Microsoft Fabric.
• Familiarity with ServiceNow development/architecture and related modules (APIs, IntegrationHub, Flow Designer, Virtual Agent, Now Assist, AI Agents, CMDB, ITSM, CSM, HRSD).
• Experience with Docker, Kubernetes, Terraform, CI/CD, cloud-native services, data orchestration, monitoring, or observability tools.
• Enterprise consulting or professional services experience and relevant certifications are a plus.

Travel & Location

• Location indicated as hybrid/remote options; expected travel up to 25–50% based on client needs.

Success in the First 6 Months

• Build trusted relationships with client stakeholders and delivery teams; deliver one or more Data Intelligence/AI solutions from prototype to production; establish secure ingestion, retrieval, and integration capabilities; improve AI reliability through data preparation, retrieval strategies, prompt/context engineering, and observability.