Staff AI Engineer
New
T
TypeformAI software
For this role, we can hire candidates based in the UK, Ireland, Germany, Portugal, Spain or the Netherlands.Full-TimeStaff
Salary$170,000—$210,000 USD; In addition to the base, we offer a 5-10% bonus depending on your level and performance.
Apply NowOpens the employer's application page
Job Details
- Required Skills
- AWSDockerPythonKubernetesPyTorchFastAPITerraformLLMLangChain
Requirements
- Significant experience building and operating machine learning or AI systems in production, with technical leadership beyond individual projects.
- Experience leading complex engineering initiatives across teams from ambiguous requirements to measurable production outcomes.
- Strong Python and software engineering skills, including the ability to contribute directly to production code.
- Experience designing production services and APIs, such as with FastAPI.
- Practical experience building generative AI applications using large language models, RAG, tool use, or agentic systems.
- Strong understanding of enterprise RAG, including retrieval architecture, chunking, embeddings, reranking, evaluation, and monitoring.
- Experience defining evaluation approaches and using evidence to guide model, architecture, and release decisions.
- Experience with frameworks such as PyTorch, LangChain, LangGraph, or similar technologies.
- Experience designing and operating cloud systems using AWS, Docker, Kubernetes, Terraform, and CI/CD practices.
- Experience with event-driven processing, vector databases, and machine learning lifecycle tools such as Kafka and MLflow, or comparable technologies.
- Experience establishing observability and diagnosing production issues using tools such as Datadog or OpenSearch.
- Experience mentoring engineers and influencing technical decisions across teams.
Responsibilities
- Shape Research Flow’s technical direction and lead architectural decisions across AI-assisted study design, adaptive conversations, and research synthesis.
- Own ambiguous AI engineering problems from defining the problem and exploring approaches through production delivery.
- Design and build generative AI applications using large language models, RAG, vector search, tool use, and agentic systems.
- Build reusable services and APIs that enable product teams to deliver AI capabilities consistently.
- Guide machine learning services and workflows using Python, Docker, Kubernetes, and AWS.
- Design reliable batch and real-time processing pipelines and improve model management, deployment, and monitoring.
- Define evaluation strategies and release criteria for generative AI applications, including automated benchmarks and production monitoring.
- Improve retrieval quality and build security, privacy, and safeguards into AI system design.
- Establish technical standards, mentor engineers, and improve testing, observability, security, incident response, and deployment practices.
- Work with Product and Engineering partners to prioritize AI investments, define measurable outcomes, and communicate technical risks and trade-offs.
View Full Description & ApplyYou'll be redirected to the employer's site
