Job Description
Overview About Business Unit: The Automotive Practice at Epsilon is a rapidly growing team, driving growth for major players in the automotive industry - from Original Equipment Manufacturers (OEMs) to dealerships across North America. Part of a 1,600-member multinational team, the practice provides the automotive world’s largest service reminder platform, alongside agency services and digital media solutions. A leader in the automotive space, the team supports over 50% of auto dealerships in North America and maintains relationships with over 280 million customers. Home to innovation and ground breaking technology, our Auto team leads the game in developing outstanding software and solutions for hyper-personalized digital marketing. We are seeking an experienced (7-12 years) Lead AI Engineer to design, build, and deploy AI-powered applications that leverage modern LLM ecosystems, Agentic AI architectures, and intelligent automation frameworks. This role requires deep expertise in end-to-end AI system development, from solution architecture and model orchestration to production deployment and scaling. You will lead the development of Agentic AI systems, Retrieval-Augmented Generation (RAG) pipelines, and multi-agent workflows, enabling intelligent applications that interact with enterprise systems, data platforms, and external tools. The ideal candidate combines strong software engineering field with cutting edge AI expertise, enabling the delivery of robust, scalable, and production-grade AI solutions. Click here to view how Epsilon transforms marketing with 1 View, 1 Vision and 1 Voice. Responsibilities AI Application Architecture Design and develop AI-native applications powered by LLMs and agent frameworks. Architect end-to-end AI pipelines, including ingestion, embedding, retrieval, reasoning, and response generation. Define scalable AI system architectures supporting real-time and batch AI workloads. Agentic AI Development Build and orchestrate multi-agent AI systems capable of autonomous reasoning and task execution. Implement agent workflows using modern orchestration frameworks. Design tool-enabled agents that integrate with enterprise systems, APIs, and databases. RAG & Knowledge Systems Develop Retrieval-Augmented Generation (RAG) pipelines for enterprise knowledge systems. Implement vector search and semantic retrieval using modern vector databases. Optimize document chunking, embedding strategies, and retrieval quality. AI Orchestration & Frameworks Build AI workflows using frameworks such as: LangChain LangGraph LangSmith Implement advanced AI workflow orchestration and stateful agent pipelines. Model Context Protocol & Integrations Implement integrations using Model Context Protocol (MCP) to connect AI systems with enterprise tools and data sources. Build AI-enabled automation workflows across internal platforms. Production Deployment Deploy AI services in production environments with monitoring, scaling, and observability. Implement CI/CD pipelines for AI applications. Ensure model reliability, performance, and cost optimization. Automation & Observability Implement AI observability, evaluation, and monitoring frameworks. Build automated pipelines for testing, validation, and continuous improvement of AI systems. Technical Leadership Lead and mentor AI engineers and developers. Establish standard processes for AI system architecture and development. Evaluate emerging AI tools, frameworks, and technologies. Qualifications Core AI & LLM Expertise Strong experience building LLM-powered applications. Deep understanding of: Agentic AI architectures Retrieval-Augmented Generation (RAG) Multi-agent systems Tool-using AI agents AI Frameworks & Tools Experience with modern AI frameworks such as: LangChain LangGraph LangSmith Vector Databases Hands-on experience with vector databases, such as: Pinecone Chroma Programming Languages Strong software engineering skills in: Python AI Infrastructure & Deployment Experience with: Containerization and microservices Cloud platforms (AWS, Azure) Model deployment and inference optimization AI service scaling and cost optimization Data & Retrieval Systems Experience with embedding models and semantic search Knowledge graph or hybrid retrieval experience is a plus Preferred qualifications Non-Technical: Experience in automotive marketing Excellent Analytical and problem solving skills Ability to diagnose and troubleshoot problems quickly Motivated to learn new applications and domains Strong time management skills Ability to take full ownership of tasks and projects Experience with Agile/SCRUM process Behavioral Attributes: Great teammate with excellent interpersonal skills Excellent verbal and written communication Possess Can-Do attitude to overcome challenges Self-motivated and directed What We Offer Opportunity to build next-generation AI platforms Work with cutting-edge Agentic AI and LLM technologies High-impact role shaping AI product strategy and architecture Collaborative and innovation driven engineering culture Additional Information Epsilon is a global data, technology and services company that powers the marketing and advertising ecosystem. For decades, we’ve provided marketers from the world’s leading brands the data, technology and services they need to engage consumers with 1 View, 1 Vision and 1 Voice. 1 View of their universe of potential buyers. 1 Vision for engaging each individual. And 1 Voice to harmonize engagement across paid, owned and earned channels. Epsilon’s comprehensive portfolio of capabilities across our suite of digital media, messaging and loyalty solutions bridge the divide between marketing and advertising technology. We process 400+ billion consumer actions each day using advanced AI and hold many patents of proprietary technology, including real-time modeling languages and consumer privacy advancements. Thanks to the work of every employee, Epsilon has been consistently recognized as industry-leading by Forrester, Adweek and the MRC. Epsilon is a global company with more than 9,000 employees around the world. Our pillars aren't just words. They're how we show up every day. People centricity: We focus on employee well-being in an environment where colleagues truly care about each other. Collaboration: We work together, support one another, and collectively achieve goals. Growth: There are endless opportunities for growth through learning, development and career advancement. Innovation: We drive progress through cutting-edge solutions and forward-thinking approaches. Flexibility: We’ve created a balance between work and personal life, and we encourage adaptability to solve problems creatively. Our values guide us to create value for our clients, our people and consumers. Act with integrity Work together to win together Innovate with purpose Respect all voices Empower with accountability These pillars and values are our foundation—shaping our culture, guiding our decisions, and uniting us in common purpose. Epsilon is an Equal Opportunity Employer. Epsilon is committed to promoting diversity, inclusion, and equal employment opportunities by using reasonable efforts to attract, recruit, engage and retain qualified individuals of all ethnicities and backgrounds, including, but not limited to, women, people of color, LGBTQ individuals, people with disabilities and any other underrepresented groups, traits or characteristics.
Core AI & LLM Expertise Strong experience building LLM-powered applications. Deep understanding of: Agentic AI architectures Retrieval-Augmented Generation (RAG) Multi-agent systems Tool-using AI agents AI Frameworks & Tools Experience with modern AI frameworks such as: LangChain LangGraph LangSmith Vector Databases Hands-on experience with vector databases, such as: Pinecone Chroma Programming Languages Strong software engineering skills in: Python AI Infrastructure & Deployment Experience with: Containerization and microservices Cloud platforms (AWS, Azure) Model deployment and inference optimization AI service scaling and cost optimization Data & Retrieval Systems Experience with embedding models and semantic search Knowledge graph or hybrid retrieval experience is a plus Preferred qualifications Non-Technical: Experience in automotive marketing Excellent Analytical and problem solving skills Ability to diagnose and troubleshoot problems quickly Motivated to learn new applications and domains Strong time management skills Ability to take full ownership of tasks and projects Experience with Agile/SCRUM process Behavioral Attributes: Great teammate with excellent interpersonal skills Excellent verbal and written communication Possess Can-Do attitude to overcome challenges Self-motivated and directed What We Offer Opportunity to build next-generation AI platforms Work with cutting-edge Agentic AI and LLM technologies High-impact role shaping AI product strategy and architecture Collaborative and innovation driven engineering culture
AI Application Architecture Design and develop AI-native applications powered by LLMs and agent frameworks. Architect end-to-end AI pipelines, including ingestion, embedding, retrieval, reasoning, and response generation. Define scalable AI system architectures supporting real-time and batch AI workloads. Agentic AI Development Build and orchestrate multi-agent AI systems capable of autonomous reasoning and task execution. Implement agent workflows using modern orchestration frameworks. Design tool-enabled agents that integrate with enterprise systems, APIs, and databases. RAG & Knowledge Systems Develop Retrieval-Augmented Generation (RAG) pipelines for enterprise knowledge systems. Implement vector search and semantic retrieval using modern vector databases. Optimize document chunking, embedding strategies, and retrieval quality. AI Orchestration & Frameworks Build AI workflows using frameworks such as: LangChain LangGraph LangSmith Implement advanced AI workflow orchestration and stateful agent pipelines. Model Context Protocol & Integrations Implement integrations using Model Context Protocol (MCP) to connect AI systems with enterprise tools and data sources. Build AI-enabled automation workflows across internal platforms. Production Deployment Deploy AI services in production environments with monitoring, scaling, and observability. Implement CI/CD pipelines for AI applications. Ensure model reliability, performance, and cost optimization. Automation & Observability Implement AI observability, evaluation, and monitoring frameworks. Build automated pipelines for testing, validation, and continuous improvement of AI systems. Technical Leadership Lead and mentor AI engineers and developers. Establish standard processes for AI system architecture and development. Evaluate emerging AI tools, frameworks, and technologies.