Generative AI Engineer

Aspect; Greater London; Hybrid; GBP 100,000 - 160,000; Full time

Job summary

Aspect in London is seeking an experienced Generative AI Engineer to design, build, and scale multi-agent systems that power core business processes. You will own agent harnesses, guardrails, observability, and AI automation across customer service, field operations, and internal workflows in production.

You will partner with Product, Design, and Operations to translate business needs into scalable AI applications, mentor junior engineers, and help shape the company’s broader AI strategy in a

Qualifications

• 3+ years in AI/ML, with at least 1 year focused on Generative AI and NLP.

Responsibilities

• Design, build, and manage production multi-agent systems, including hierarchical agents, swarms, and complex coordination and hand-off logic for multi-tasking and automation.
• Implement guardrails across the stack, including input/output validation, policy enforcement, PII redaction, hallucination and safety checks, and human-in-the-loop controls for high-risk actions.
• Design and deliver AI automation that removes manual effort across customer service, field operations, and internal workflows, tying agent actions to measurable business outcomes.

Skills

Generative AI

Multi-agent systems

Python

AI observability

LangChain

CI/CD for AI

Tool integration

Tools

LangGraph

CrewAI

AutoGen

Guardrails AI

LangSmith

Langfuse

Arize Phoenix

Weighs & Biases

PyTorch

TensorFlow

Vertex AI

Job description

At Aspect, we are one of London's largest property maintenance teams, covering more trades than anyone else and operating 24/7. After more than 25 years of trusted service to thousands of residential and commercial customers, we are entering an exciting phase of rapid digital transformation. We are investing heavily in AI and automation to reimagine how we deliver customer service, field operations, and internal workflows.

We are now looking for an experienced Generative AI Engineer to lead the charge in designing, building, and scaling the multi-agent systems that will run at the core of our business.

The Role

As our Generative AI Engineer, you will own the design and delivery of production-grade agentic AI. This means going far beyond calling a model. You will build and maintain the agent harnesses that let large language models reason, use tools, and coordinate as multi-agent systems, wrap them in the guardrails that keep them safe and reliable, drive real AI automation across the business, and stand up the observability needed to know exactly what those systems are doing in production.

You will partner closely with stakeholders across Product, Design, and Operations to translate business needs into intelligent, scalable applications. This role is hands-on and strategic. You will build solutions end-to-end while also helping shape the company's broader AI strategy.

We are looking above all for someone who can design, orchestrate, and manage complex multi-agent systems, and keep them dependable at scale.

You Will

• Design, build, and manage production multi-agent systems, including hierarchical agents, swarms, and complex coordination and hand-off logic for multi-tasking and automation.
• Build and maintain robust agent harnesses covering tool use, memory, planning loops, and orchestration, so agents run predictably and can be extended by the team.
• Implement guardrails across the stack, including input and output validation, policy enforcement, PII redaction, hallucination and safety checks, and human-in-the-loop controls for high-risk actions.
• Design and deliver AI automation that removes manual effort across customer service, field operations, and internal workflows, tying agent actions to measurable business outcomes.
• Stand up AI observability from day one, including tracing, logging, evaluation, cost and latency monitoring, and alerting, so we can debug, measure, and continuously improve live systems.
• Develop and fine-tune LLMs and implement Retrieval-Augmented Generation (RAG) pipelines for specialised knowledge tasks.
• Integrate GenAI tools into platforms such as WordPress and Salesforce to enhance customer-facing services.
• Work with multi-modal models across text, vision, and voice to build versatile and conversational AI systems.
• Collaborate with stakeholders across departments to identify high-impact AI use cases, translate requirements, and deliver solutions that align with business goals.
• Mentor junior engineers, promote best practices, and contribute to AI architecture and strategic planning.
• Drive responsible AI development with a focus on fairness, security, and governance in compliance with ethical standards.

Required Skills and Experience

• 3+ years in AI/ML, with at least 1 year focused on Generative AI and NLP.
• Proven experience designing and running multi-agent systems in production, not just prototypes.
• Hands-on experience building agent harnesses and orchestration logic with frameworks such as LangGraph, CrewAI, AutoGen, or similar.
• Practical experience implementing guardrails and safety layers using tools such as Guardrails AI, NeMo Guardrails, or equivalent custom approaches.
• Experience with AI observability and evaluation tooling such as LangSmith, Langfuse, Arize Phoenix, Helicone, or Weights and Biases.
• Strong programming skills in Python, proficient in libraries such as NumPy, Pandas, scikit-learn, PyTorch, and TensorFlow.
• Expertise in LLM architectures (OpenAI, Anthropic, LLaMA, Mistral, and similar) and RAG implementation.
• Familiarity with frameworks like LangChain and LlamaIndex.
• Experience with CI/CD for AI (GenAIOps), model monitoring, and cloud platforms such as Google Vertex AI, AWS SageMaker, or Azure AI.
• Knowledge of AI security, model explainability, and Responsible AI principles.
• Experience building or integrating voice-enabled chatbots and multi-modal systems.
• Hands-on experience deploying AI services in WordPress or similar CMS environments.
• Excellent communication skills and the ability to explain complex AI concepts to non-technical stakeholders.
• Strong stakeholder management and project delivery experience across cross-functional teams.

Preferred Qualifications

• Experience working with open-source AI tools and LLM.
• Background in AI ethics, fairness, compliance, or regulatory frameworks.
• Familiarity with Salesforce, vector databases (Pinecone, Weaviate, FAISS), graph-based reasoning, or knowledge graphs.
• Experience in property maintenance, home services, or customer service automation (not required, but a bonus).

Location and Working Arrangement

This is a full-time, office-based role at our London office. It is not a remote or hybrid position. We work closely as a team and want you in the office with us, collaborating in person with Product, Design, and Operations as we build these systems together.

Why Join Us?

• Be a key player in shaping the AI future of a rapidly growing company.
• Own the multi-agent systems that will sit at the heart of how the business runs.
• Work in a fast-moving, collaborative environment with autonomy and real impact.
• Work on cutting-edge agentic AI, guardrails, automation, and observability from the ground up.
• Supportive team culture that values innovation, transparency, and personal growth.