Senior Agentic AI Engineer, AI Automation

We’re looking for an Agentic AI Engineer  to join our AI Automation team, building production-grade AI applications that help internal users automate routine execution and focus on more complex, high-value challenges. 

We are looking for a senior software engineer with strong AI engineering experience  who has designed, built, deployed, and operated real-world applications in production. 

You will be responsible for designing and implementing the agentic LLM orchestration  behind our solutions, while also contributing across the wider application stack. This includes building reliable Python backend services, React/TypeScript frontends, APIs, databases and SQL-based data workflows, and integrating AI capabilities into well-designed production systems. 

You should have hands-on experience with system design and production software architecture, including designing scalable and maintainable services, data flows, APIs, authentication, error handling, and integration between system components. 

You should also be comfortable with DevOps and production operations, including CI/CD pipelines, cloud deployment, infrastructure configuration, monitoring, logging, debugging and maintaining applications after release. Experience with AWS  is a plus. 

This role involves working with global stakeholders across different time zones. From time to time, you may be required to attend meetings outside your normal working hours. We support flexible working arrangements, allowing you to adjust your working hours accordingly when this is needed. 

Why join Mintel? We are the world's leading market intelligence agency and technology underpins our success. We help our clients understand consumers and consumer markets, and we aspire to provide the market intelligence behind every great business decision. Our technology allows us to deliver data, insights, and opinions in a compelling way to our clients across the globe. 

Mintel is committed to building and supporting a diverse workforce, providing opportunities for all. 22% of our Engineering team and 23% of our Engineering leaders are women. We offer flexible working options and provide support, development and growth opportunities. 

We support a Hybrid working approach. Most of our colleagues work 3 days a week in our KL office and the rest of the week remotely.

What You Will Do  

• Design, build, deploy, and operate production-grade full-stack applications, working across React and TypeScript frontends, Python (FastAPI/Django) backend services, SQL databases, APIs, authentication, and system integrations. 

• Design and implement agentic AI systems, including LLM orchestration, tool use, workflows, retrieval and other patterns required to integrate generative AI reliably into production applications. 

• Design and implement robust evaluation frameworks for LLM and agentic AI systems, defining appropriate quality metrics and test datasets, running automated and human evaluations, and using evaluation results to identify regressions and continuously improve system quality, reliability, and performance. 

• Join a high functioning Agile team, working closely with business stakeholders to understand needs and deliver solutions. 

• Own technical design decisions and contribute to system architecture, considering scalability, reliability, maintainability, security, performance, observability, and appropriate trade-offs between different approaches. 

• Deploy and operate applications in cloud environments, contributing hands-on to DevOps practices including CI/CD, infrastructure configuration, monitoring, logging, troubleshooting, and production support. Our applications primarily operate across AWS. 

• Develop a strong understanding of the market research and consulting domain. You will work closely with our consultants and business stakeholders to understand how they work, the problems they solve for clients, and where AI and automation can provide meaningful value. We believe understanding the domain is essential to building useful AI applications rather than simply applying technology to a problem. 

• Develop features or solve technical problems within the context of your team’s sprint. Often this will be as an individual contributor or pairing within the team, however collaborating with Engineers and Architects from other teams is also important from time to time. 

• Help your team to deliver high quality, reliable software via our code review and QA practices and contribute to the evolution of these over time.  

• Make your voice heard when we’re discussing implementation trade-offs within the team or technical solution possibilities with our stakeholders.   

What We Are Looking For

• Strong professional hands-on experience building applications with LLMs and agentic AI, using technologies or frameworks such as OpenAI Agents SDK, LangGraph, AutoGen, CrewAI, or equivalent approaches. 

• Strong hands-on experience with LLM evaluation, including designing evaluation strategies, defining meaningful metrics and datasets, implementing automated evaluation pipelines, and evaluating non-deterministic AI systems using techniques such as deterministic checks, human evaluation, and LLM-as-a-judge. 

• An understanding of the challenges involved in taking generative AI from prototype to production, including evaluation, reliability, observability, error handling, security, cost, latency, and managing the non-deterministic nature of LLM-based systems. 

• Strong full-stack software engineering skills, including React and TypeScript on the frontend and Python (FastAPI or Django), SQL, APIs, authentication, and system integrations on the backend. 

• Hands-on experience designing production systems, with a good understanding of software architecture, distributed system considerations, API design, data flows, security, reliability, scalability, and maintainability. 

• Hands-on DevOps and cloud experience, including deploying and operating applications, CI/CD, monitoring, logging, debugging production issues, and working with cloud infrastructure. Experience with AWS is particularly valuable, with Azure experience also beneficial. 

• A product and problem-solving mindset. You should be interested in understanding the underlying business problem and user workflow rather than simply implementing the requested technology. 

• The ability and willingness to quickly develop domain expertise. Prior market research or consulting experience is not required, but you will be expected to learn how our consultants work, understand the types of problems they solve for clients, and use that knowledge when designing solutions. 

• The ability to operate with the autonomy expected of a senior engineer, taking ownership of ambiguous technical problems, evaluating different approaches, making well-reasoned decisions, and driving work through to production. 

• Strong communication skills, with the ability to explain technical concepts, architectural decisions, and trade-offs to diverse business stakeholders without losing essential context or relying unnecessarily on technical jargon. 

 What We Offer

• A culture that supports true collaboration whilst embracing remote working.  

• Flexible start times and end times.  

• Approach to personal development where we encourage individuals to grow and share what they’ve learned.  

• Social events, both within the department and across the company.  

• Generous annual leave and wider circle employee benefits.  

• Additional one day off to celebrate your birthday.  

• Membership in Employee Resource Groups (Mintel Diversity, Mintel Wellness, and Mintel Gives).  

• Giving back is part of our culture with this in mind, Mintel gives employees 2 days' leave per year to join local volunteering activities organised by our Mintel Gives (where applicable).  

• Mental health and wellbeing support via Modern Health App.  

• Beautifully designed offices foster collaboration and fun.