Duration: 6 months contract
Location: Dublin (2 days onsite)
In this contract role, you will build and deploy production-grade LLM/GenAI pipelines for information extraction and transformation, with strong validation, quantitative evaluation, and error analysis, integrated into downstream systems
Responsibilities
Design, develop and deploy production-quality AI/ML solutions using Large Language Models, traditional machine learning, statistical methods and deterministic approaches.
Apply modern GenAI techniques to solve complex problems involving information extraction, interpretation, transformation and reasoning over complex data.
Develop robust end-to-end pipelines for preparing data, applying models, validating outputs and integrating results into downstream systems.
Evaluate and improve solution performance, reliability and accuracy through testing, error analysis and iterative refinement.
Work effectively with data science, engineering and analytic engineering teams to integrate, operationalise and support solutions in production environments.
Requirements
5+ years of experience in data analysis, statistical modelling, and machine learning
Strong programming skills in Python and SQL
Hands‑on experience designing and implementing LLM / GenAI solutions, including workflows for retrieval, context selection, extraction, validation, and refinement, combined with deterministic and ML approaches as needed.
Experience defining evaluation datasets and metrics for extraction tasks and implementing regression tests to prevent quality degradation
Experience working with structured, semi-structured or unstructured data
Demonstrated systems‑level thinking, strong technical problem‑solving skills, and ability to work effectively within a technical delivery team
Preferred Qualifications
Experience with healthcare data, particularly claims, payment integrity, provider, contract, policy or reimbursement‑related data
Advanced degree in Applied Mathematics, Physics, Computer Science, Statistics, Data Science or a related technical field
Experience building document extraction/document understanding solutions from PDFs, including handling tables, inconsistent formats, and noisy text
Demonstrated ability to evaluate emerging AI/LLM methods and apply them pragmatically to real‑world problems
#J-18808-Ljbffr