United States (Remote) •United Kingdom (Remote)
Remote
Senior
Full Time
remoteAImachine learninggenerative AIPythonAWSKubernetesMLflow
Requirements
- •At least four years of experience building and deploying machine learning or AI systems in production
- •Strong Python and software engineering skills
- •Experience building production services using Python frameworks such as FastAPI
- •Practical experience developing generative AI applications using large language models, RAG, tool use, or agentic systems
- •Experience with frameworks such as PyTorch, LangChain, LangGraph, or similar technologies
- •Strong understanding of enterprise RAG systems including chunking, embeddings, retrieval, reranking, evaluation, and monitoring
- •Experience creating automated evaluations for generative AI applications
- •Experience with AWS, Docker, Kubernetes, Terraform, and continuous integration and deployment practices
- •Experience using services such as AWS SageMaker or AWS Bedrock
- •Experience with Kafka, vector databases, or other technologies used for real time and high dimensional data processing
- •Experience managing machine learning workflows using MLflow
- •Experience monitoring production systems with tools such as Datadog or OpenSearch
- •Ability to balance quality, speed, reliability, scalability, and cost when making technical decisions
- •Strong communication skills and experience collaborating with Product, Engineering, and Data teams
What You'll Do
- •Design, build, and deploy generative AI capabilities across Typeform’s products, with a key contribution to Research Flow
- •Develop applications using large language models, RAG, vector search, and agentic systems
- •Build services and APIs that allow product teams to integrate AI capabilities into customer experiences
- •Turn prototypes into reliable production systems with clear measures of performance and quality
- •Explore new ways for customers to collect, understand, and act on information using AI
- •Design and operate machine learning services and workflows using Python, Docker, Kubernetes, and AWS
- •Build reliable pipelines for batch and real time processing using technologies such as Kafka and Airflow
- •Design solutions using vector databases to support retrieval, recommendations, personalisation, and semantic search
- •Use MLflow to manage experiments, model versions, registries, and deployments
- •Improve the reliability, performance, scalability, and cost efficiency of AI systems
- •Build automated evaluation pipelines for generative AI applications, including conversational and analytical capabilities
- •Develop benchmarks that measure accuracy, relevance, reliability, fairness, latency, and cost
- •Evaluate retrieval strategies including chunking, embeddings, context selection, and reranking
- •Monitor AI systems in production and identify opportunities to improve quality and performance
- •Create safeguards that reduce unexpected behaviour and protect customer data
- •Establish reusable patterns and technical standards for building, evaluating, and releasing AI systems
- •Help teams make informed decisions about models, frameworks, infrastructure, performance, and cost
- •Apply strong engineering practices across testing, security, observability, version control, and deployment
- •Share technical knowledge and support the development of other engineers
- •Keep up with relevant AI research, tools, and engineering practices
- •Partner with Product, Engineering, Data Science, Data Engineering, and Analytics teams to connect AI investments with customer and business needs
- •Work with Data Scientists to turn experiments and models into reliable production services
- •Communicate technical concepts, risks, and tradeoffs clearly to technical and nontechnical partners
- •Contribute to technical planning and help shape the direction of AI across Typeform
Nice to Have
- •Experience working in a B2B SaaS product company
- •Experience with orchestration tools such as Airflow or Argo Workflows
- •Familiarity with SQL, Spark, Snowflake, or other data processing technologies
- •Experience building systems that combine structured data, unstructured data, and generative AI
- •Experience with AI security, privacy, responsible AI, prompt injection protection, or data leakage prevention
- •Experience improving the latency and cost of AI systems operating at scale
