Senior Ai Engineer

Role overview

A senior AI engineering role focused on designing, building, and operating the production systems behind a suite of AI-powered customer products. The work spans generative AI applications, enterprise retrieval-augmented generation, agentic workflows, model evaluation, machine learning pipelines, and the infrastructure needed to run these reliably at scale. This is a hands-on engineering position with strong ownership of systems, technical standards, and the path from prototype to production.

Responsibilities

- Design, build, and deploy generative AI capabilities using large language models, RAG, vector search, and agentic systems. - Develop services and APIs that allow product teams to integrate AI capabilities into customer-facing experiences. - Build and operate scalable ML services and pipelines using Python, Docker, Kubernetes, and AWS, including batch and real-time processing with technologies like Kafka and Airflow. - Design retrieval solutions using vector databases to support semantic search, recommendations, and personalisation, and manage experiments, versions, and deployments with MLflow. - Create automated evaluation pipelines and benchmarks covering accuracy, relevance, reliability, fairness, latency, and cost, and monitor production systems for quality improvements. - Establish reusable engineering patterns and technical standards for building, evaluating, and releasing AI, while partnering with product, data science, data engineering, and analytics teams.

Requirements

- At least four years of experience building and deploying machine learning or AI systems in production. - Strong Python and software engineering skills, including experience with production frameworks such as FastAPI. - Practical experience developing generative AI applications with LLMs, RAG, tool use, or agentic systems, and familiarity with frameworks like PyTorch, LangChain, or LangGraph. - Strong understanding of enterprise RAG systems, including chunking, embeddings, retrieval, reranking, evaluation, and monitoring. - Experience with AWS, Docker, Kubernetes, Terraform, and CI/CD practices, plus services such as AWS SageMaker or AWS Bedrock. - Experience with Kafka, vector databases, MLflow, and production monitoring tools such as Datadog or OpenSearch, with the ability to balance quality, speed, reliability, scalability, and cost.

Nice to have

- Experience in a B2B SaaS product company. - Familiarity with orchestration tools such as Airflow or Argo Workflows. - Comfort with SQL, Spark, Snowflake, or similar data processing technologies. - Experience building systems that combine structured and unstructured data with generative AI. - Background in AI security, privacy, responsible AI, prompt injection protection, or data leakage prevention. - Experience improving the latency and cost of AI systems operating at scale.