Senior AI Agent Engineer

Meetsocial is a full-service, socially-led growth marketing agency delivering guaranteed business performance for startups, scale-ups and enterprise brands through performance media, social and content across culturally fluent, full-funnel journeys.

With 1000+ growth marketing practitioners and $6B worth of proprietary cultural data points, we’ve helped thousands of the world’s top companies build brands that are adored, not endured in today’s attention economy.

We are cultural matchmakers and media activists delivering culture-powered performance by locating cultural & consumer behavioural signals that enable brands to meet their most relevant audiences in their own spaces, communities & fandoms.

Meetsocial. We grow brands in-culture.

The Role

We're looking for a Senior AI Agent Engineer to design, build, and scale intelligent agent systems that power real business applications from single-agent workflows to complex multi-agent collaboration.

What You’ll Be Doing

• Design, develop, and deploy AI Agent systems, including single-agent and multi-agent collaboration, tool use, and both workflow-driven and autonomous agent patterns
• Build scalable, maintainable agent architectures using leading frameworks such as PydanticAI, LangGraph, and LangChain
• Evaluate and work hands-on with leading LLMs (OpenAI, Claude, Gemini, DeepSeek, Qwen, LLaMA, etc.), driving model selection, prompt design, context engineering, and performance optimization
• Design and implement core capabilities including RAG (Retrieval-Augmented Generation), long-term memory, context management, tool orchestration, and plan-and-execute logic
• Integrate agents with real business systems such as APIs, databases, search systems, code execution environments, and third-party SaaS tools
• Drive performance optimization, reliability, and observability to improve reasoning efficiency, success rates, and system controllability
• Collaborate cross-functionally with product, algorithm, frontend, and business teams to bring AI Agents to scale in production

What We're Looking For

Required:

• Strong proficiency in Python, with solid engineering fundamentals including async programming, modular design, and common backend frameworks
• Hands-on experience with leading LLMs — their capabilities, limitations, and differences, including reasoning, function calling, and structured output
• Experience with at least one Agent development framework or paradigm, with a solid understanding of core agent components (Prompt, Memory, Tool, Planner, Executor, Reflection, etc.)
• Strong grasp of common AI Agent architecture patterns, such as ReAct, Plan & Execute, Reflection, and multi-agent collaboration
• Good coding practices, strong debugging skills, and the ability to troubleshoot complex issues

Nice to Have:

• Experience with TypeScript/Node.js; agent frontend or full-stack development experience is a plus
• Hands-on experience with RAG systems, vector databases (Milvus, Qdrant, Weaviate, FAISS, etc.), or search systems
• Proven track record shipping AI applications or agent products (e.g., copilots, intelligent assistants, automated operations, intelligent analytics)
• Practical experience with AI Agent safety, controllability, evaluation, and continuous optimization