Staff AI Engineer

This is a fully remote position, open to applicants in United Kingdom, +5 more countries.

📋 Description

• Shape the technical vision for Research Flow and the wider AI systems at Typeform.

• Collaborate with Product and Engineering leaders to establish technical direction and set delivery priorities.

• Oversee the architecture for AI-enhanced study design, adaptive conversations, and research synthesis.

• Take ownership of intricate AI engineering challenges from initial exploration to production delivery.

• Design and develop generative AI applications utilizing LLMs, RAG, vector search, tool utilization, and agentic systems.

• Create reusable AI services and APIs for product teams.

• Direct the architecture of machine learning services and workflows using Python, Docker, Kubernetes, and AWS.

• Design dependable batch and real-time processing pipelines using Kafka and Airflow.

• Enhance management of experiments, model versions, registries, and deployment using tools like MLflow.

• Define evaluation strategies, benchmarks, release criteria, and production monitoring for generative AI.

• Improve retrieval quality through chunking, embeddings, context selection, and reranking techniques.

• Integrate security, privacy, and protective measures against unanticipated model behaviors into system design.

• Establish reusable standards for developing, evaluating, deploying, and operating AI systems.

• Mentor engineers and assist technical leads.

• Collaborate with Product, Engineering, Data Science, Data Engineering, and Analytics teams to align technical efforts with customer outcomes.

⛳️ Requirements

• Extensive experience in building and operating machine learning or AI systems in production, with technical leadership that extends beyond individual projects.

• Proven track record of leading complex, cross-team engineering initiatives from vague requirements to quantifiable production results.

• Proficient in Python and software engineering practices.

• Experience in designing production services and APIs using frameworks such as FastAPI.

• Hands-on experience in creating generative AI applications utilizing large language models, RAG, tool usage, or agentic systems.

• Deep understanding of enterprise RAG systems, including retrieval architecture, chunking, embeddings, reranking, evaluation, and monitoring.

• Experience in defining evaluation methodologies and employing evidence to guide decisions regarding models, architecture, and releases.

• Familiarity with PyTorch, LangChain, LangGraph, or similar technologies.

• Significant experience with AWS, Docker, Kubernetes, Terraform, and CI/CD practices.

• Knowledge of AWS SageMaker or AWS Bedrock.

• Experience with event-driven processing, vector databases, and ML lifecycle tools such as Kafka and MLflow, or equivalent technologies.

• Expertise in establishing observability and diagnosing production issues using Datadog or OpenSearch.

• Ability to balance delivery speed, quality, reliability, scalability, security, and cost.

• Capability to influence technical decisions across teams without formal authority.

• Experience in mentoring engineers and enhancing team effectiveness.

🏝️ Benefits

• Fully remote by design.

• Equal-opportunity employer dedicated to diversity and non-discrimination.

• Collaborative culture based on respect, transparency, and trust.