AI Agent Engineer – Marketing Automation & Intelligence

We are looking for a highly skilled AI Agent Engineer having 3-5 years of experience, to design and build intelligent, production-grade AI systems that power marketing automation, campaign optimization, and customer engagement. This role combines deep expertise in Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), and AI agent frameworks with practical experience integrating solutions into real-world marketing ecosystems. The ideal candidate will be hands-on, innovation-driven, and capable of deploying scalable, secure AI solutions that deliver measurable business outcomes.

Key Responsibilities

• Design and develop intelligent AI agents for marketing automation and campaign optimization
• Build social listening agents to track brand mentions, sentiment analysis, and competitor activity across digital channels
• Develop AI-driven lead scoring and prospecting systems integrated with CRM platforms
• Implement Retrieval-Augmented Generation (RAG) architectures for knowledge-based marketing assistants
• Integrate AI agents with marketing platforms such as HubSpot and other third-party tools
• Optimize prompts, workflows, context management, memory handling, and performance
• Deploy AI agents securely on cloud infrastructure with scalability and reliability in mind
• Monitor, evaluate, and continuously improve model accuracy, performance, and ROI
• Maintain technical documentation, architecture diagrams, and best practices

Technical Requirements

Must-Have Skills

• Strong Python programming skills
• Hands-on experience with LLM APIs (OpenAI, Azure OpenAI, Anthropic, vLLM, or open-source LLMs)
• Experience with AI agent frameworks (LangChain, CrewAI, AutoGen, or similar)
• Solid prompt engineering expertise and prompt optimization techniques
• Experience building and consuming RESTful APIs
• Hands-on experience with vector databases (Pinecone, Qdrant, PGVector, etc.)
• Strong understanding of RAG architecture and implementation patterns
• Familiarity with Git and version control best practices