Lead Software Engineer (AI Enabled Solutions)

The Lead Software Engineer (AI Enabled Solutions) will collaborate with business users, business analysts, project managers, and other stakeholders, assuming responsibility for the successful delivery of projects, system enhancements, and initiatives in accordance with established timelines and quality standards.

This role will also provide solutions in integrating AI technologies into the core application development processes, utilizing AI-assisted tools to achieve enhancements efficiently and with high quality.

• Responsible in conducting impact assessments, system design, development, testing, implementation, and post-deployment verification, utilizing AI-assisted tools, LLMs and intelligent workflows.
• Design and develop solutions based on user requirements, ensuring adherence to mutually agreed timelines, quality benchmarks, and performance standards.
• Analyse both functional and technical solution requirements, contributing to the creation of comprehensive functional and technical specifications.
• Demonstrate hands-on development expertise in Java/J2EE applications and Oracle PL/SQL programming, with the ability to deliver tasks independently.
• Participate in source code reviews, code merges, and assessments of code quality.
• Design and implement AI-driven features, such as automated debugging, code generation, and process optimization across supported platforms.
• Build and refine RAG pipelines while integrating LLMs to enhance core application capabilities.
• Design Graph RAG strategies that utilize structured knowledge graphs by improving reasoning and contextual understanding.
• Use prompt engineering, loop engineering, and agentic tools to create reliable automation.
• Collaborate regularly with business users, business analysts, project managers, and other stakeholders regarding SIT, UAT, production support, user queries, and database-related issues.
• Govern AI practices within the team by establishing integration standards, evaluation guidelines, safety measures, cost management, and documentation.
• Oversee deployment, monitoring, and optimization on cloud platforms to maintain uninterrupted operation of essential services.
• Provide technical guidance, conduct mentoring sessions, review code and architecture and ensure timely delivery of AI-driven solutions.

• Possesses Bachelor Degree in Computer Science, Business Information Systems, Insurance, or a related area is preferred.
• Candidate must possess 8 to 12 years of relevant professional experience, including a minimum of 2 years of experience integrating AI/LLM features into production applications.
• Advanced design and programming abilities with Java and server-side technologies such as Java, J2EE, Struts, Spring, Hibernate, and REST APIs.
• Solid technical background in SQL and PL/SQL programming.
• Capable of thriving in a fast-moving, collaborative environment with minimal supervision.
• Experience and knowledge of microservices architecture will be added advantage.
• Experience within the insurance industry is a plus.
• Excellent leadership, problem-solving, and interpersonal communication skills.
• Demonstrated leadership in guiding teams to deliver enhancements, resolve bugs, and develop new features using AI-assisted tools within core, production environments.
• Extensive experience with large language models (LLMs) such as OpenAI, Claude, Qwen, DeepSeek, and open-source alternatives, including practical integration for automation, information retrieval, and content generation.
• In-depth hands-on knowledge of RAG architectures encompassing data ingestion strategies, chunking techniques, hybrid retrieval (combining keyword and semantic methods), reranking, and grounding methods to minimize hallucinations.
• Advanced proficiency in prompt engineering and loop engineering (system prompts, chain-of-thought development, ReAct-style loops, self-reflection, and iterative enhancement).
• Proven expertise in designing and utilizing agentic tools (function/tool calling, custom integrations) alongside API design for seamless connection of AI functionalities to backend and frontend application infrastructures.
• Comprehensive understanding and experience with databases (Vector database, Relational database)) for AI workloads.
• Strong experience on DevOps and Production deployment skills on cloud platforms (AWS, GCP, Azure etc), including containerization, CI/CD, and monitoring.
• Strong understanding of AI technologies, trends and best practices.