Senior GenAI Developer

About the role

We are looking for an experienced AI/LLM Engineer to join our Data‑Driven Customer Insights team and lead the development of Large Language Model (LLM) and AI‑driven capabilities for the OneCustomer product. You will work in a DevOps environment, creating production‑ready AI components that enhance how we engage with healthcare professionals and internal stakeholders.

Key responsibilities

• Lead all LLM‑related activities, including prompt engineering, compliance‑rule prompts, user‑feedback integration, parameter tuning, and model/API version upgrades.
• Collaborate with Commercial, Medical, and Analytics stakeholders to translate business needs into effective system prompts, few‑shot learning, and domain ontologies.
• Manage vector databases and knowledge graphs that support Retrieval‑Augmented Generation (RAG) workflows.
• Implement observability systems covering monitoring, logging, performance tracking, error detection, and real‑time dashboards.
• Oversee LLM model configurations, deployments, endpoint setup, version control, and infrastructure optimization for scalability, load‑balancing, and high availability.
• Work closely with MLOps, QA, Data Science, and Product teams to ensure robust testing and continuous improvement.
• Engineer compliance‑aligned prompts and system rules to reduce false positives and ensure market safety.

Required profile

• Bachelor’s or Master’s degree in Computer Science, Data Science, AI/ML, Engineering or a related field.
• Proven experience building AI/ML solutions in DevOps environments, especially with LLMs, RAG pipelines, or knowledge graphs.
• Strong understanding of AI compliance, observability, and production deployment practices.

Required skills

• Large Language Models (LLM)
• Prompt Engineering
• Retrieval‑Augmented Generation (RAG)
• Knowledge Graphs
• Vector Databases
• Observability (Monitoring, Logging, Dashboards)
• Model Deployment & Endpoint Management
• Version Control & Infrastructure Optimization
• Load Balancing & High Availability
• MLOps & DevOps
• AI/ML & Data Science
• Quality Assurance (QA)
• Few‑shot Learning
• Parameter Tuning
• Compliance Engineering