Staff AI Engineer - Typeform

About Typeform

Typeform is a refreshingly different form builder. We help over 150,000 businesses collect the data they need with forms, surveys, and quizzes that people enjoy. Designed to look striking and feel effortless to fill out, Typeform drives 500 million responses every year—and integrates with essential tools like Slack, Zapier, and HubSpot.

Typeform is fully remote by design. For this role, we can hire candidates based in the UK, Ireland, Germany, Portugal, Spain, or the Netherlands.

About the Team

The AI Engineering team builds the systems and capabilities behind Typeform’s AI products, including Research Flow, our platform for combining quantitative research with deeper qualitative insights.

We use machine learning, large language models, RAG, and agentic systems to help customers collect, understand, and act on information in more conversational and personalised ways. Through Research Flow, this includes helping customers design studies, run AI-moderated conversations with adaptive follow-up questions, and turn responses into useful insights.

The team owns the journey from experimentation through to production, encompassing AI application development, evaluation, infrastructure, deployment, observability, reliability, and performance. You will work closely with Product Managers, Software Engineers, Data Scientists, Data Engineers, and Analytics teams.

About the Role

As a Staff AI Engineer at Typeform, you will play a central role in shaping the technical direction of Research Flow and the AI systems supporting our broader products. You will take ownership of complex engineering challenges spanning multiple teams, from architecture definition to production operations.

Your scope covers generative AI applications, enterprise RAG systems, agentic workflows, model evaluation, machine learning pipelines, and production cloud infrastructure.

What You Will Do

Shape Technical Direction

• Partner with Product and Engineering leaders to translate Research Flow’s product ambitions into a clear technical direction and delivery priorities.
• Lead architectural decisions across AI-assisted study design, adaptive conversations, and research synthesis.
• Identify critical technical constraints and dependencies early.
• Define how AI capabilities, data flows, and services integrate as the product evolves.
• Balance immediate delivery needs with long-term reliability, scalability, and maintainability.

Lead AI Engineering Initiatives

• Take technical ownership of ambiguous problems from exploration through production delivery.
• Design and build generative AI applications using LLMs, RAG, vector search, tool use, and agentic systems.
• Stay close to implementation through prototyping, production code, design reviews, and debugging.
• Build reusable services and APIs to help product teams deliver AI capabilities consistently.

Build Scalable AI Foundations

• Guide the architecture of machine learning services and workflows using Python, Docker, Kubernetes, and AWS.
• Design reliable batch and real-time processing pipelines using technologies such as Kafka and Airflow.
• Establish patterns for retrieval, vector search, model orchestration, and structured/unstructured data processing.
• Improve experiment tracking, model versioning, registries, and deployments using MLflow.
• Identify and resolve performance, reliability, and cost bottlenecks across AI infrastructure.

Set Standards for AI Quality

• Define evaluation strategies and release criteria for generative AI applications.
• Guide automated benchmarks covering accuracy, relevance, reliability, fairness, latency, and cost.
• Assess AI-generated follow-up quality and groundedness of summaries/insights.
• Lead retrieval quality improvements across chunking, embeddings, context selection, and reranking.
• Incorporate security, privacy, and safeguards against unexpected model behavior.

Raise Engineering Standards & Collaboration

• Establish reusable patterns and technical standards for AI development and deployment.
• Mentor engineers and support other technical leads in growing their architectural judgment.
• Partner with Product and Engineering to prioritize AI investments based on customer needs, technical feasibility, and business impact.

What You Bring

• Significant experience building and operating machine learning or AI systems in production with proven technical leadership.
• Track record of leading complex engineering initiatives across cross-functional teams.
• Strong software engineering foundation in Python with direct contributions to production code.
• Experience designing production services and APIs using frameworks such as FastAPI.
• Practical experience building generative AI applications using LLMs, RAG, tool use, or agentic architectures.
• Deep understanding of enterprise RAG systems (retrieval architecture, embeddings, reranking, evaluation, monitoring).
• Experience with frameworks such as PyTorch, LangChain, LangGraph, or equivalent tooling.
• Strong cloud infrastructure experience using AWS, Docker, Kubernetes, Terraform, and modern CI/CD practices.
• Familiarity with AWS SageMaker, AWS Bedrock, Kafka, and MLflow.
• Experience establishing observability and diagnosing production issues using tools like Datadog or OpenSearch.

Extra Awesome

• Experience in a B2B SaaS product company.
• Experience building conversational AI, adaptive interviewing, or automated summarisation systems.
• Experience working with multimodal applications (text, audio, video).
• Experience evolving shared AI platforms used by multiple product engineering teams.
• Experience with workflow orchestration (Airflow, Argo Workflows) and data platforms (SQL, Spark, Snowflake).
• Experience with AI safety, prompt injection defense, and data privacy safeguards.