Gen AI Engineer

The Role

We're looking for a Gen AI Engineer to join an agile AI engineering team developing high-value, AWS-based Gen AI solutions.

The focus is firmly on Machine Learning, Gen AI, LLMs, data and AI engineering, with hands-on development across RAG, prompt engineering, model deployment and APIs.

Responsibilities

• Design and build Gen AI solutions using LLMs, RAG, LangChain, LangSmith and LlamaIndex, including prompt engineering and fine-tuning.
• Develop ML systems, feature engineering pipelines and model deployment solutions, optimising model inference and performance.
• Build Python-based APIs using FastAPI or Flask and develop scalable data pipelines and AI services.
• Deploy and manage AI solutions across AWS, including SageMaker, EC2 and EKS, with supporting infrastructure and data platforms.
• Work with large datasets to perform analysis, train/retrain models, run experiments and continuously improve AI solutions.

About You

• 3-5 years' hands-on Machine Learning Engineering experience, with strong Python and/or Java development skills.
• Strong practical experience with Gen AI, LLMs, RAG, LangChain/LangSmith, LlamaIndex, prompt engineering and/or fine-tuning.
• Excellent SQL skills and experience working across databases such as Postgres/RDS and Snowflake, with deep data analysis experience.
• Strong AWS experience, ideally including SageMaker, EC2/EKS, alongside tools such as Airflow and Terraform.
• Experience developing production-quality AI/ML solutions, with a genuine interest in Gen AI and emerging ML technologies. Experience with Solr, Elasticsearch or OpenSearch would be a bonus.

Why Join?

You'll join a collaborative, agile engineering team within a major financial services organisation, working on innovative, high-business-value AI solutions designed to automate challenging manual processes.

The role offers a hybrid working model in Dublin and the opportunity to work across modern cloud, data and Gen AI technologies.