Senior AI Solution Engineer — Generative AI & RAG

About the role
We are looking for a Senior AI Solution Engineer with a strong focus on Generative AI and Retrieval-Augmented Generation (RAG). You will help digitize existing services and workflows by developing AI-powered applications that convert organizational expertise into scalable digital services. You will work closely with domain experts, product owners and engineers to design, build and deploy secure, usable solutions that deliver relevant information, guidance and decision support to end users.

Responsibilities

• Map business needs and capture, structure and encode expert knowledge into machine-readable formats for retrieval and reasoning.
• Design, build and maintain RAG pipelines (data ingestion, vectorization, retrieval, prompt engineering, and response filtering) tailored to the business domain.
• Evaluate, select and integrate large language models (LLMs) and related tools — with current environment using Azure and Anthropic Claude — and integrate with other providers where appropriate.
• Integrate AI components with existing systems via robust APIs and scalable cloud architectures on Azure.
• Define and implement evaluation frameworks for quality, safety, fairness, privacy and usability of AI outputs; monitor and iterate based on metrics and user feedback.
• Implement production-grade deployments: containerization, orchestration, CI/CD, monitoring and incident handling to ensure reliability and scalability.
• Collaborate with product, design and subject-matter experts to ensure solutions meet real-world assessment and decision-making needs (recruitment, development, coaching, analytics).

Requirements

• 5+ years of hands-on experience in applied AI/ML engineering, with significant experience designing and delivering AI-driven products.
• Proven experience building RAG solutions and working with LLMs in production; experience with Anthropic Claude and OpenAI or similar models is required.
• Strong software engineering skills — primarily Python — and experience building REST API integrations with downstream systems.
• Experience with Azure cloud services and deploying models / services on Azure; familiarity with containerization (Docker) and orchestration (Kubernetes).
• Knowledge of data pipelines, vector stores and search/embedding workflows, and evaluation methodologies for LLM outputs (accuracy, safety, hallucination mitigation).
• Solid understanding of security, data privacy and compliance considerations when building AI systems that handle sensitive or personal data.
• Excellent communication skills and the ability to translate domain expertise into technical requirements and product features.
• Experience in assessment, cognitive science, HR-tech, or related domains is a strong plus given the company's focus on digital cognitive and executive assessment tools.