Senior AI Agent Engineer (Machine Learning)

Zendesk; York and North Yorkshire; Hybrid; GBP 60,000 - 80,000; Full time

Job summary

A leading customer engagement software company in York is looking for an AI Agent Engineer to develop and deploy intelligent agents that utilize large language models. This role involves designing AI solutions that can handle complex tasks, integrating them with enterprise systems, and optimizing performance metrics. The ideal candidate has a strong background in Python and relevant AI fields, along with experience in tool integration and AI evaluation.

Benefits

Guided technical learning

Flexible working hours

Diversity and inclusion initiatives

Qualifications

• Experience in designing scalable AI agents using Python.
• Ability to integrate AI solutions into enterprise systems.
• Strong understanding of LLM evaluation and optimization.

Responsibilities

• Design and develop autonomous agents leveraging large language models.
• Integrate AI agents with existing systems to streamline workflows.
• Establish key metrics for evaluating AI agent performance.

Skills

Python

Multi-step reasoning

Tool integration

Prompt engineering

Education

Ph.D./Masters in Computer Science, AI, ML, or NLP

Tools

FastAPI

LLM SDKs

AWS

Job description

Overview

The Agentic Tribe is revolutionizing the chatbot and voice assistance landscape with Gen3, a cutting-edge AI Agent system that is goal-oriented, dynamic, and conversational. Gen3 leverages a multi-agent architecture and advanced language models to deliver personalized experiences, handle complex tasks, and respond to off-script inquiries in real-time.

About the Role

We are seeking a passionate and experienced AI Agent Engineer to design, develop, and deploy intelligent, autonomous agents that leverage Large Language Models (LLMs) to streamline operations. You will build the cognitive architecture for AI-powered applications, enabling agents to reason, plan, and execute multi-step tasks, and you will communicate complex technical concepts to both technical and non-technical stakeholders.

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 strengths, weaknesses, and cost-effectiveness for specific use cases.
• Drive the entire lifecycle of AI Agent deployment—collaborate with cross-functional teams (product managers, ML scientists, software engineers) to understand user needs and deliver effective agent solutions.
• Troubleshoot, debug, and optimize complex AI systems for production reliability, performance, and scalability.
• 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.

Core Technical Competencies

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

Bonus Points (Preferred Qualifications)

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

The Interview Process

We are transparent about what to expect in our interview process:

1. Initial Call with Talent Team – 15 mins
2. Interview with a Hiring Team member – 45 mins
3. Take-home technical challenge
4. Technical interview with two developers – ~1 hour
5. Final interview with CTO/Engineering Manager or Director – ~45 mins

About Zendesk

Zendesk builds software for better customer relationships, empowering organizations to engage customers effectively. With presence in multiple regions, Zendesk provides scalable solutions and a strong focus on inclusion and diversity.

Zendesk is an equal opportunity employer. We value diversity and inclusion and do not discriminate based on race, color, religion, national origin, age, sex, gender, gender identity, gender expression, sexual orientation, marital status, medical condition, disability, military or veteran status, or any other characteristic protected by law.

By submitting your application, you agree that Zendesk may collect your personal data for recruiting and related purposes. The Candidate Privacy Notice explains data processing and rights.

Hybrid: This role has a hybrid schedule, requiring some in-office presence. Specific in-office days are determined by the hiring manager.