Senior AI Agent Engineer in London

The Agentic Tribe is revolutionizing the chatbot and voice assistance landscape with Gen3, a cutting-edge AI Agent system that's pushing the boundaries of conversational AI. Gen3 is not your typical chatbot; it's a goal-oriented, dynamic, and truly conversational system capable of reasoning, planning, and adapting to user needs in real-time. By leveraging a multi-agent architecture and advanced language models, Gen3 delivers personalized and engaging user experiences, moving beyond scripted interactions to handle complex tasks and "off-script" inquiries with ease.

About the Role: We are seeking a passionate and experienced AI Agent Engineer to join our team. In this role, you will be dedicated to innovating at the forefront of AI technology, with a focus on designing, developing, and deploying intelligent, autonomous agents that leverage Large Language Models (LLMs) to streamline operations. You will be a key player in building the cognitive architecture for our AI-powered applications, creating systems that can reason, plan, and execute complex, multi-step tasks. You’ll effectively communicate complex technical concepts to both technical and non-technical stakeholders, including those outside your immediate team.

What You'll Do (Responsibilities):

• Design and develop robust, stateful, and scalable AI agents using Python and modern agentic frameworks (e.g., LangChain, LlamaIndex).
• Integrate AI agent solutions with existing enterprise systems, databases, and third-party APIs to create seamless, end-to-end workflows.
• Evaluate and select appropriate foundation models and services from third-party providers (e.g., OpenAI, Anthropic, Google), analyzing their strengths, weaknesses, and cost-effectiveness for specific use cases.
• Drive the entire lifecycle of AI Agent deployment—Collaborate closely with cross-functional teams, including product managers, ML scientists, and software engineers, to understand user needs and deliver effective, high-impact agent solutions.
• Troubleshoot, debug, and optimize complex AI systems to ensure optimal performance, reliability, and scalability in production environments.
• Establish and improve platforms for evaluating AI agent performance, defining key metrics to measure success and guide iteration.
• Document development processes, architectural decisions, code, and research findings to ensure knowledge sharing and maintainability across the team.

Core Technical Competencies:

• LLM-Oriented System Design: Designing multi-step, tool-using agents (LangChain, Autogen). Deep understanding of prompt engineering, context management, and LLM behaviour quirks (e.g., hallucinations, determinism, temperature effects). Implementing advanced reasoning patterns like Chain-of-Thought and multi-agent communication.
• Tool Integration & APIs: Integrating agents with external tools, databases, and APIs (OpenAI, Anthropic) in secure execution environments.
• Retrieval-Augmented Generation (RAG): Building and optimizing RAG pipelines with vector databases, advanced chunking, and hybrid search.
• Evaluation & Observability: Implementing LLM evaluation frameworks and monitoring for latency, accuracy, and tool usage.
• Safety & Reliability: Defending against prompt injection and implementing guardrails (Rebuff, Guardrails AI) and fallback strategies.
• Performance Optimization: Managing LLM token budgets and latency through smart model routing and caching (Redis).
• Planning & Reasoning: Designing agents with long-term memory and complex planning capabilities (ReAct, Tree-of-Thought).
• Programming & Tooling: Expert in Python, FastAPI, and LLM SDKs; experience with cloud deployment (AWS/GCP/Azure) and CI/CD for AI applications.

Bonus Points (Preferred Qualifications):

• Ph.D / Masters in a relevant field (e.g., Computer Science, AI, Machine Learning, NLP).
• Deep understanding of foundational ML concepts (attention, embeddings, transfer learning).
• Experience adapting academic research into production-ready code.
• Familiarity with fine-tuning techniques (e.g., PEFT, LoRA).

The Interview Process: We are excited to learn more about you, so we want to be transparent about what you can expect from our interview process:

• Initial Call with Talent Team - 15 mins
• Interview with one member of the Hiring Team - 45 minutes
• Take-home technical challenge
• A technical interview with two of our developers to talk more in-depth about your technical experience and answer any questions you might have - 1 hour
• Final interview with 2 of the following: CTO or Engineering Manager/Director - 45 minutes

About Zendesk: Zendesk builds software for better customer relationships. It empowers organizations to improve customer engagement and better understand their customers. Zendesk products are easy to use and implement. They give organizations the flexibility to move quickly, focus on innovation, and scale with their growth. More than 100,000 paid customer accounts in over 150 countries and territories use Zendesk products. Based in San Francisco, Zendesk has operations in the United States, Europe, Asia, Australia, and South America.