About this role
Designing architecture and testing new approaches take up the daily routine in this hands-on role. Engineers on this team build generative AI applications, enterprise RAG systems, and agentic workflows that power products like Research Flow. This platform helps businesses combine quantitative research with qualitative insights by running AI-moderated conversations and turning responses into actionable data.
Typeform created this position to shape the technical direction of its AI capabilities and connect individual features into dependable customer experiences. The person in this seat takes ownership of complex engineering challenges that span multiple teams, from early experimentation through to production deployment. Ideal candidates bring significant experience operating machine learning systems in production and demonstrate strong technical leadership without needing direct reports.
What you will do
- Shape the technical direction of Research Flow by partnering with product and engineering leaders to translate product ambitions into clear delivery priorities.
- Take technical ownership of ambiguous problems from initial exploration through to production delivery, writing production code and building reusable services.
- Guide the architecture of machine learning services using Python, Docker, Kubernetes, and AWS while establishing patterns for retrieval and vector search.
- Define evaluation strategies and release criteria for generative AI applications, including automated benchmarks for accuracy, reliability, and cost.
- Establish reusable patterns and technical standards for building, evaluating, deploying, and operating AI systems safely at scale.
- Collaborate closely with product managers, software engineers, and data scientists to align technical work with customer outcomes and business impact.
What you need
- Significant experience building and operating machine learning or AI systems in production with evidence of technical leadership.
- Strong Python and software engineering skills with the ability to contribute directly to production code and design APIs using frameworks like FastAPI.
- Practical experience building generative AI applications using large language models, retrieval-augmented generation, tool use, or agentic systems.
- Strong understanding of enterprise RAG systems including retrieval architecture, chunking, embeddings, reranking, and evaluation.
- Experience designing and operating cloud systems using AWS, Docker, Kubernetes, Terraform, and continuous integration practices.
- Familiarity with event-driven processing, vector databases, machine learning lifecycle tools, and observability platforms like Datadog.
Skills and tech stack
Questions candidates ask
What is the remote work policy for this position?
Typeform is fully remote by design. For this role, candidates can be based in the UK, Ireland, Germany, Portugal, Spain, or the Netherlands.
What technologies and tools will I be working with?
The tech stack includes Python, FastAPI, PyTorch, LangChain, LangGraph, Docker, Kubernetes, Terraform, AWS, Kafka, Airflow, MLflow, and Datadog.
What does the AI Engineering team actually build?
The team builds systems and capabilities behind Typeform's AI products, including Research Flow, which combines quantitative research with qualitative insights through conversational interfaces.
What kind of leadership responsibilities are involved?
This is a hands-on individual contributor role with influence beyond a single project. You will lead through technical judgement, delivery, and collaboration while mentoring engineers.