Lead Software Engineer

Lead Software Engineer

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