Job Summary Responsible for designing, developing, and maintaining LLM-powered applications including application integration to key banking systems. The engineer is expected to be knowledgeable of current software packages related to the development of LLM-powered applications and is up-to-date with up and coming advances in the field. The engineer is expected to be well-verse with software development life cycle including requirements gathering, model development and integration, testing, and deployment. How will you contribute Lead the solution architecture and development of simple to complex applications that integrate Large Language Models (LLM) with banking core systems via advanced patterns (e.g., Agentic Orchestration, Multi-Agent Systems, RAG, and MCP integration, Prompt Engineering, etc. ) Develop front-end web-based user interfaces that will expose Agentic applications to the workforce. Ensure reliability, usability, and responsiveness of the deployed application in the productionenvironment. Engineer robust LLM Evaluation frameworks and maintain accuracy standards and implement controls that safeguards the application from LLM-based hallucinations. Define engineering best practices (CI/CD, Unit Testing for AI, Code Reviews) and cascade design patterns and techniques to data engineers to foster an environment of knowledge sharing and co-development Develop and optimize full-stack interfaces (Front-end and API layers) that expose Agentic applications to the workforce, ensuring high availability and low latency. Conduct deep-dive research into emerging Agentic technologies and prototype their application within the bank's legacy infrastructure What will make you successful Degree in Mathematics, Statistics, Computer Science, Management Information Systems, or related field Experience building LLM-powered applications (production or strong POC). 4-5 years of total Software Engineering experience, with at least 2 years experience in developing, implementing, and deploying LLM-based applications Strong programming skills in Python. Proficiency in SQL for data transformation and analytics. Deep understanding of Vector Database architecture (e.g., Milvus, Pinecone) and advanced RAG retrieval strategies. Experience setting up LLM Ops / ML Ops pipelines (CI/CD, Evaluation, Monitoring) Certificates and training in the field is highly desirable (e.g. Google AI certificate, Kaggle, OpenAI etc.)
