Staff AI Engineer

Join Typeform as a Staff AI Engineer, where you will shape the technical direction of Research Flow and the AI systems that support our products. You will take ownership of complex engineering challenges, lead architectural decisions, and design and build generative AI applications. This is a hands-on individual contributor role with influence beyond a single project.

Experience with AI security, privacy, responsible AI, prompt injection protection, or data leakage prevention

Responsibilities

• Prendre en charge des défis d'ingénierie complexes, de la définition de l'architecture à la livraison et à l'exploitation des systèmes de production.
• Diriger les décisions architecturales concernant la conception d'études assistées par l'IA, les conversations adaptatives et la synthèse de la recherche.
• Concevoir et construire des applications d'IA générative en utilisant des modèles de langage de grande taille, des systèmes RAG, la recherche vectorielle, l'utilisation d'outils et des systèmes agentiques.
• Experience establishing observability and diagnosing production issues using tools such as Datadog or OpenSearch
• Sound judgement when balancing delivery speed, quality, reliability, scalability, security, and cost
• Experience mentoring engineers and improving the effectiveness of the teams around you

Requirements

• A strong understanding of enterprise RAG systems, including retrieval architecture, chunking, embeddings, reranking, evaluation, and monitoring
• Familiarity with services such as AWS SageMaker or AWS Bedrock
• Experience designing production services and APIs using frameworks such as FastAPI
• The ability to influence technical decisions across teams and build alignment without relying on formal authority
• Strong Python and software engineering skills, with the ability to contribute directly to production code
• Strong experience designing and operating cloud systems using AWS, Docker, Kubernetes, Terraform, and continuous integration and deployment practices
• A track record of leading complex engineering initiatives across teams, from ambiguous requirements to measurable production outcomes
• Practical experience building generative AI applications using large language models, RAG, tool use, or agentic systems
• Experience with frameworks such as PyTorch, LangChain, LangGraph, or similar technologies
• Significant experience building and operating machine learning or AI systems in production, with evidence of technical leadership beyond your own projects
• Experience with event-driven processing, vector databases, and machine learning lifecycle tools such as Kafka and MLflow, or comparable technologies
• Experience defining evaluation approaches and using evidence to guide model, architecture, and release decisions

Experience working in a B2B SaaS product company

• Experience building conversational AI, adaptive interviewing, or automated analysis and summarisation systems
• Experience working with text, audio, or video in AI applications
• Experience evolving shared AI infrastructure or platforms used by multiple product teams
• Experience with orchestration tools such as Airflow or Argo Workflows
• Experience materially improving the latency, reliability, or cost of AI systems operating at scale

Preferred

• Familiarity with SQL, Spark, Snowflake, or other data processing technologies

Pay

USD 170,000 - 210,000