Senior AI Engineer: GenAI & LLM/Ops (Remote)

We are looking for a Senior AI Engineer to join our Belfast-based Data & AI Platform Team in building a next-generation data platform which will leverage aPriori's proprietary data to deliver powerful insights and AI capabilities.

As a Senior AI Engineer, you will play a critical role in shaping and delivering AI-powered features within aPriori's Data Platform, delivered via APIs and our product surfaces. You will design and implement production-grade solutions that leverage both generative AI with LLMs and traditional AI/ML. Working closely with Product Management and product teams, you will integrate AI capabilities into our products, enabling AI-powered insights, automation, and new user experiences that increase aPriori's value to our customers.

This role is hands on and highly collaborative: you will design and implement LLM-driven features, leverage and extend a modern data pipeline, and contribute to building scalable AI infrastructure using cloud-based AI/ML services such as AWS Bedrock/Sagemaker, GCP Vertex AI, TensorFlow, PyTorch.

Location: Belfast, NI (Hybrid) or Remote UK

• Design and build production ready AI/ML systems, with an emphasis on Standard Model LLM powered product and platform features.
• Leverage LLM tooling/APIs such as LangChain and MCP connectors to implement retrieval augmented generation (RAG), copilot assistants and agentic workflows.
• Partner with Product Management and product teams to translate requirements into AI powered capabilities that surface directly in user facing products.
• Apply MLOps and LLMOps best practices: monitoring, evaluation, prompt versioning, cost/performance optimization.
• Combine traditional AI/ML with modern GenAI approaches to deliver hybrid solutions where appropriate.
• Collaborate with Data Engineers to establish a scalable data pipeline that serves structured data shaped for LLM consumption, feature store data for traditional AI, and Trad/GenAI enhanced insights for internal and customer facing BI use cases.
• Mentor and upskill peers in core AI/ML and LLMOps practices, raising the overall AI/ML competency of the team.
• Stay current with developments in GenAI, LLMOps, generative AI safety frameworks, and evaluate their potential for adoption within the platform.

• Hands on familiarity with Prompt Engineering by leveraging LLM frameworks such as LangChain.
• Strong programming skills in Python and familiarity with modern data/ML pipelines.
• Solid understanding of data engineering practices (ETL/ELT, streaming, orchestration with Airflow/Temporal, dbt, Kafka, etc.).
• Knowledge of LLMOps/MLOps practices: CI/CD for ML, model monitoring, drift detection, evaluation metrics, governance.
• Strong collaboration and communication skills: able to partner with Product, Platform, and Data teams to drive AI features from concept to production.
• Demonstrated ability to mentor and upskill engineers, particularly in data/ML workflows.
• Skilled in designing/building/deploying/operating LLM standard model powered features in production (chatbots, copilots, RAG systems, agents).
• Proficient in working with traditional cloud AI/ML platforms such as Amazon Sagemaker, GCP Vertex AI, or Azure ML and frameworks such as TensorFlow, PyTorch, scikit learn.

• 7+ years of professional software engineering experience, including 3+ years experience in traditional AI/ML and 1+ year experience in building LLM applications on standard models.
• Bachelor's or Master's in Computer Science, AI/ML, Data Science, or related field (or equivalent experience).

A team environment where your experience is valued, your voice is heard, and the work that you do makes an impact for our customers and employees. Competitive compensation and unique benefits including pension match, private medical & dental, flexible time off, aPriori days, and more in a dynamic, growing, innovative environment.