Job Title

The Senior GenAI Engineer will lead the design and development of large language model (LLM) based solutions to support an AI-powered recommendation and assistant platform for insurance sales advisors. This role focuses on architecting scalable GenAI pipelines from scratch, including Retrieval-Augmented Generation (RAG), agentic workflows, and LLM integrations. The engineer will work closely with data, infrastructure, and engineering teams to develop production-ready AI solutions, evaluate models, and implement robust GenAI microservices within a secure enterprise cloud environment. The position requires strong expertise in machine learning, NLP, GenAI technologies, and cloud-native architectures, with the ability to translate business needs into scalable AI solutions. KEY RESPONSIBILITIES Architect and design LLM-based solutions including RAG pipelines, embeddings, fine-tuning strategies, and evaluation frameworks Build scalable GenAI microservices and integrate them with internal enterprise systems Develop advanced prompt engineering strategies, agentic workflows, and safety guardrails for LLM systems Evaluate open-source and commercial LLM models for performance, cost efficiency, and risk mitigation Collaborate with data teams to prepare training datasets, knowledge bases, and analytics pipelines Oversee ingestion and refresh of knowledge bases and data pipelines supporting RAG architectures Implement monitoring, validation frameworks, and closed-loop measurement to continuously improve AI solution quality Ensure compliance with enterprise security standards and insurance regulatory requirements Work with engineering teams to productionize GenAI solutions using scalable cloud architectures Partner with business stakeholders to define use cases, requirements, and solution delivery strategies Document architecture, data sources, and technical processes supporting AI solutions Present insights, model performance metrics, and business impact to senior stakeholders Support change management and adoption strategies for AI-driven solutions Mentor junior engineers and promote best practices in AI engineering and system design Collaborate with cross-functional teams including Data Infrastructure, Backend, and Frontend teams Maintain accurate task tracking and documentation using tools such as Jira REQUIRED QUALIFICATIONS 6+ years of experience in machine learning, artificial intelligence, or NLP engineering Minimum 2+ years of hands-on experience working with GenAI and LLM-based applications Strong expertise in Retrieval-Augmented Generation (RAG), vector databases, embeddings, and model evaluation techniques Hands-on experience with LLM platforms such as OpenAI, Azure OpenAI, Anthropic, Llama, or similar models Experience designing and deploying GenAI solutions in production environments Proficiency in Python and experience building data pipelines for AI systems Strong knowledge of cloud-native architectures, preferably on Microsoft Azure Experience building scalable AI systems in enterprise environments Strong understanding of machine learning techniques and statistical modeling methods Experience working with SQL, data modeling, and relational or NoSQL databases Strong problem-solving, analytical thinking, and communication skills Ability to collaborate effectively with cross-functional teams and business stakeholders Bachelors degree in Computer Science, Engineering, Mathematics, or equivalent practical experience PREFERRED QUALIFICATIONS Experience designing agentic AI systems and integrating AI agents into enterprise workflows Familiarity with BI and visualization tools such as Power BI or Tableau Experience working within financial services or insurance domain environments Experience with Hadoop or other distributed data platforms Strong understanding of MLOps or GenAIOps practices for managing AI lifecycle #J-18808-Ljbffr