Staff Agentic AI Engineer - Marketing

This position is listed on behalf of a partner company, who manages all applications and next steps. Our partner is looking for a Staff Agentic AI Engineer - Marketing based in United States.

This is a senior individual contributor role focused on building production-grade agentic AI systems for enterprise marketing and customer experience use cases.
You will help shape the architecture of AI agents that can reason, retrieve information, use tools, and automate complex business workflows.
The role combines hands-on software engineering with advanced work across LLMs, RAG, embeddings, evaluation, guardrails, and agent orchestration.
You will tackle challenging problems involving reliability, latency, cost, safety, observability, and task completion in real-world production environments.
Working closely with product, platform, and engineering teams, you will turn emerging AI capabilities into scalable and measurable platform features.
Your work will influence how enterprise customers deploy AI-powered experiences and automation at significant scale.
This opportunity is ideal for an experienced AI engineer who thrives on ambiguity, technical innovation, and building sophisticated systems that move from experimentation into production.

Accountabilities

• Design, build, and continuously improve production-grade agentic AI systems supporting web-based and chat-based marketing experiences using grounded and structured enterprise data.
• Architect agent workflows incorporating reasoning, tool use, retrieval, guardrails, escalation paths, workflow orchestration, and performance monitoring.
• Evaluate emerging agent frameworks and orchestration patterns, including LangGraph, LangChain, Deep Agent, Claude Agent, OpenAI Agent, and related technologies, with a focus on enterprise marketing applications.
• Develop and maintain comprehensive LLM evaluation systems, including LLM-as-judge workflows, regression evaluations, guardrail testing, quality metrics, and analysis of production behavior.
• Diagnose and optimize agent performance across prompts, tool selection, retrieval quality, latency, cost, reliability, task completion, and failure modes.
• Design and implement RAG and embedding-based capabilities that enable enterprise knowledge access, grounded generation, and intelligent automation.
• Build scalable Python services and platform components for deployment and operation in AWS cloud environments.
• Partner with product, platform, and engineering teams to translate emerging agentic AI capabilities into reliable, scalable platform functionality.
• Establish engineering practices and technical standards that support continuous optimization, quality, observability, and maintainability of agentic systems.
• Stay current with developments in LLMs, agent architectures, AI coding tools, evaluation methodologies, retrieval technologies, and enterprise automation, applying relevant advances to production systems.

Requirements

• Bachelor’s degree or higher in a quantitative discipline such as Computer Science, Statistics, Engineering, Mathematics, or a related field.
• 5–7+ years of experience in AI/ML engineering, applied machine learning, natural language processing, AI systems development, or a closely related discipline.
• 3–5 years of experience applying AI, data science, and machine learning to marketing-oriented use cases.
• Experience working with enterprise marketing and customer data platforms such as Adobe Experience Platform, Adobe Commerce/Magento, Adobe Real-Time CDP, Adobe Target, Adobe Analytics, or Customer Journey Analytics.
• Strong Python engineering skills and demonstrated experience building scalable, reliable production software systems.
• Hands-on experience with LangGraph, LangChain, or comparable agent orchestration frameworks.
• Strong understanding of RAG, embeddings, retrieval quality, knowledge-grounded generation, and enterprise knowledge access.
• Experience deploying and operating production systems in AWS cloud environments.
• Regular use of AI coding tools such as Codex, Claude Code, Cursor, or similar technologies within software development workflows.
• Strong engineering judgment, independence, ownership, and the ability to navigate ambiguous and technically complex problems as a senior individual contributor.
• A Master’s degree or higher in a quantitative field is preferred.
• Experience with knowledge graphs, enterprise knowledge modeling, retrieval, reasoning, or personalization is an asset.
• Demonstrated experience building or operating production LLM and AI agent systems, including architectures involving tool use, reasoning flows, retrieval, memory, guardrails, and orchestration.
• Experience developing AI evaluation systems, observability and tracing capabilities, or production quality measurement frameworks is highly valued.
• Experience with enterprise automation, customer experience platforms, workflow automation, or AI-powered business process automation is an asset.
• Familiarity with vector databases, search infrastructure, model routing, caching, or multi-model architectures is beneficial.
• Experience optimizing AI agent systems for latency, cost, reliability, safety, and successful task completion is strongly preferred.

Benefits

• Full-time, fully remote position available across United States.
• Opportunity to work at the forefront of enterprise agentic AI and automation.
• Hands-on involvement in advanced LLM, AI agent, RAG, evaluation, and orchestration technologies.
• Opportunity to solve complex production-scale engineering challenges for global enterprise customers.
• Senior individual contributor role with significant technical ownership and influence over platform architecture.
• Collaborative environment working closely with product, platform, and engineering teams.
• Exposure to rapidly evolving AI technologies, frameworks, coding tools, and evaluation methodologies.
• Opportunity to shape engineering best practices for scalable, reliable, and measurable agentic systems.
• Inclusive workplace committed to diversity and equal opportunity.

How Jobgether works:

We use an AI-powered matching process to ensure your application is reviewed quickly, objectively, and fairly against the role's core requirements. Our system identifies the top-fitting candidates, and this shortlist is then shared directly with the hiring company. The final decision and next steps (interviews, assessments) are managed by their internal team.

We appreciate your interest and wish you the best!

Data Privacy Notice: By submitting your application, you acknowledge that Jobgether will process your personal data to evaluate your candidacy and share relevant information with the hiring employer. This processing is based on legitimate interest and pre-contractual measures under applicable data protection laws (including GDPR). You may exercise your rights (access, rectification, erasure, objection) at any time.

#LI-CL1

We may use artificial intelligence (AI) tools to support parts of the hiring process, such as reviewing applications, analyzing resumes, or assessing responses and identifying potential inconsistencies or verification signals in application materials based on available information. These tools assist our recruitment team but do not replace human judgment. Final hiring decisions are ultimately made by humans. If you would like more information about how your data is processed, please contact us.