Software Engineer (Agentic AI), AI Automation

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

This is primarily a software engineering role focused on building production applications that incorporate Agentic AI and LLM-based capabilities . We are looking for someone with solid software engineering experience who is comfortable working across different parts of a modern web application and is excited about developing deeper expertise in Agentic AI.

You will work across the application stack, including Python backend services, React/TypeScript frontends, APIs, SQL databases, system integrations, and cloud infrastructure . A key part of your role will be designing and implementing the agentic LLM orchestration behind our applications and ensuring that these capabilities work reliably as part of a broader production system.

You will also contribute to how we evaluate and improve our LLM-based applications , helping us understand whether our AI systems are performing well, where they fail, and how changes to prompts, models, tools, retrieval, or application logic affect overall quality.

We expect our engineers to develop a good understanding of the problems they are solving. You will therefore be expected to learn about the market research and consulting domain , work closely with our business stakeholders, and understand their workflows, challenges, and client needs. We believe that understanding the domain is essential to building genuinely useful AI applications rather than simply applying technology to a problem.

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 three days a week in our KL office and the rest of the week remotely.

What You Will Do

• Build, test, deploy, and maintain production full-stack applications , working across React and TypeScript frontends, Python services using FastAPI or Django, SQL databases, APIs, authentication, and system integrations.

• Design and implement Agentic AI capabilities , including LLM orchestration, tool use, workflows, retrieval, structured outputs, and other patterns required to integrate generative AI into production applications.

• Contribute to the evaluation of LLM and Agentic AI systems , helping define evaluation datasets and meaningful quality criteria, implementing automated evaluations, analysing failures and regressions, and using the results to improve system performance.

• Contribute to technical design and system architecture , considering factors such as maintainability, scalability, reliability, security, performance, and observability.

• Deploy and operate applications in cloud environments , contributing to CI/CD, application configuration, monitoring, logging, troubleshooting, and production support. Our applications primarily operate in AWS.

• Develop a strong understanding of the market research and consulting domain , working with consultants and other business stakeholders to understand their workflows, the problems they solve for clients, and where AI and automation can provide meaningful value.

• Translate business problems into practical technical solutions , working closely with stakeholders to understand requirements and helping them understand what is technically feasible .

• Develop features and solve technical problems as part of an Agile team , working independently where appropriate while also pairing and collaborating with other Engineers and Architects.

• Help deliver high-quality, reliable software through testing, code reviews, QA practices, documentation, and continuous improvement of our engineering practices.

• Participate actively in technical discussions , contributing your perspective when evaluating implementation approaches, technical trade-offs, and potential solutions.

What We Are Looking For

• Professional experience building and deploying production software applications. We are particularly interested in candidates who have worked on applications used by real users, rather than experience limited primarily to personal projects, hackathons, or proof-of-concepts.

• Good full-stack software engineering skills , with experience in backend development using Python and technologies such as FastAPI or Django, together with SQL, APIs, authentication, and system integrations.

• Experience with, or a willingness to work across, frontend technologies such as React and TypeScript. You do not need to be equally specialised in every part of the stack.

• Hands-on experience building applications with generative AI or LLMs , with an understanding of concepts such as prompting, tool use, retrieval, structured outputs, agents, and LLM orchestration.

• Experience with LLM evaluation, or a strong understanding of evaluation approaches for LLM-based applications , including concepts such as evaluation datasets, quality metrics, deterministic evaluation, human evaluation, LLM-as-a-judge, and regression testing.

• An understanding of the challenges involved in moving generative AI beyond prototypes and into production , including reliability, observability, error handling, security, latency, cost, and the non-deterministic nature of LLM-based systems.

• A good foundation in system design and software architecture , with an understanding of areas such as API design, data flows, application boundaries, scalability, reliability, security, and maintainability.

• Exposure to DevOps and cloud environments , including areas such as application deployment, CI/CD, monitoring, logging, and debugging production issues. Hands-on AWS experience is particularly valuable.

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

• The ability and willingness to quickly develop domain knowledge . Previous experience in market research or consulting is not required , but you will be expected to learn how our consultants work and use that knowledge when designing solutions.

• The ability to work independently while knowing when to collaborate or seek input , taking ownership of your work and driving technical problems through to resolution.

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

Nice to have

• Experience with Agentic AI frameworks or SDKs such as OpenAI Agents SDK, LangGraph, AutoGen, CrewAI, or similar technologies .

• Experience implementing automated LLM evaluation pipelines as part of the development lifecycle or CI/CD process.

• Experience with AWS infrastructure and services used to deploy production web applications.

• Experience designing or operating distributed, asynchronous, or event-driven systems .

…