Senior AI Engineer - US

Role overview

A senior AI engineer opportunity focused on building and evolving generative AI capabilities for a conversational research platform that combines quantitative surveys with qualitative insights. The work spans LLM-powered applications, enterprise retrieval-augmented generation, agentic workflows, and the production infrastructure that keeps them reliable at scale. It is a hands-on engineering role with significant ownership, taking ideas from experimentation through to customer-facing experiences.

Responsibilities

- Design, build, and deploy generative AI features that support AI-moderated conversations, adaptive follow-up questions, and conversion of responses into structured insights. - Develop applications using large language models, retrieval-augmented generation, vector search, and agentic systems, including services and APIs that other product teams can integrate. - Operate machine learning services on AWS using Python, Docker, and Kubernetes, and build batch and real-time pipelines with tools such as Kafka and Airflow. - Implement vector databases to support retrieval, recommendations, personalisation, and semantic search, and manage experiments, versions, and deployments through MLflow. - Build automated evaluation pipelines and benchmarks that measure accuracy, relevance, reliability, fairness, latency, and cost, and monitor production systems for ongoing improvement. - Shape reusable patterns and technical standards for AI development, evaluation, deployment, observability, and security across the engineering organisation.

Requirements

- At least four years of experience building and deploying machine learning or AI systems in production. - Strong Python and general software engineering skills, including production services with frameworks such as FastAPI. - Hands-on experience developing generative AI applications using LLMs, RAG, tool use, or agentic systems, and familiarity with frameworks such as PyTorch, LangChain, or LangGraph. - Solid understanding of enterprise RAG, covering chunking, embeddings, retrieval, reranking, evaluation, and monitoring, plus experience creating automated evaluations for generative AI. - Experience with AWS, Docker, Kubernetes, Terraform, and CI/CD practices, including services such as SageMaker or Bedrock, and with Kafka, vector databases, and high-dimensional or real-time data processing. - Experience managing ML workflows with MLflow, monitoring production with tools such as Datadog or OpenSearch, and balancing quality, speed, reliability, scalability, and cost in technical decisions.

Nice to have

- Background in B2B SaaS, orchestration tools such as Airflow or Argo Workflows, and data processing technologies such as SQL, Spark, or Snowflake. - Experience combining structured and unstructured data with generative AI, and work in AI security, privacy, responsible AI, prompt-injection protection, or data-leak prevention. - Track record of improving latency and cost for AI systems operating at scale.

Benefits and work setup

- Fully remote role with hiring restricted to candidates based in the US Eastern timezone. - Equal-opportunity employer committed to diversity, inclusion, and a collaborative team culture.