Senior GenAI Engineer (Banking, 1-year renewable contract)

Dear Applicant, If you or someone you know is interested, please send the CV directly to quynh.nguyen@evolutionjobs.sg (most preferred, as I may overlook some CVs due to the high volume). Please note that visa sponsorship is not available at this time. Key Responsibilities • Design, build, and enhance production-grade Generative AI applications for real-world enterprise use cases. • Develop GenAI applications using LangGraph, LangChain, or similar orchestration frameworks. • Build and implement agentic workflows, Retrieval-Augmented Generation (RAG), tool calling, prompt orchestration, and context management. • Work with open-weight models and hosted LLMs, including model integration and serving patterns. • Integrate GenAI solutions with enterprise systems, APIs, backend services, data sources, and operational platforms. • Design and implement reliable and scalable backend services supporting GenAI applications. • Engineer solutions for production readiness, including logging, tracing, monitoring, evaluation, fallback mechanisms, error handling, and troubleshooting. • Develop clean, maintainable, scalable, and testable code following strong software engineering practices. • Evaluate existing technical designs, challenge weak approaches, and recommend practical and effective alternatives. • Collaborate closely with application, data, platform, infrastructure, security, and business teams to deliver end-to-end GenAI solutions. • Troubleshoot complex application, integration, model, and production issues and drive them through to resolution. • Contribute to the continuous improvement of GenAI applications, architecture, engineering practices, and delivery processes. • Work effectively in a fast-moving environment with evolving requirements and incomplete information. • Take ownership of delivery and demonstrate a pragmatic, hands-on approach focused on building useful and reliable AI products rather than over-engineering or hype. Key Requirements • 6+ years of software engineering experience, with recent hands-on experience in Generative AI application development. • Proven experience building and delivering production-grade GenAI applications, beyond prototypes, experiments, or demos. • Strong hands-on experience with LangGraph, LangChain, or similar GenAI orchestration frameworks. Practical experience with: o RAG (Retrieval-Augmented Generation) o Agentic workflows o Tool calling o Prompt orchestration o Context management • Experience integrating LLMs into real-world applications through APIs, backend services, and enterprise data sources. • Experience working with open-weight models, or strong hands-on experimentation and understanding of open-weight model deployment. • Strong backend development skills using Python, Java, or similar programming languages. • Good understanding of API design, distributed systems, scalability, and production resilience patterns. • Experience with logging, tracing, observability, monitoring, evaluation, and troubleshooting for GenAI or backend applications. • Familiarity with containerised deployment environments such as Kubernetes or OpenShift. • Strong software engineering discipline with the ability to write clean, maintainable, scalable, and testable code. • Strong analytical, debugging, and problem-solving skills. • Ability to assess technical designs critically and propose practical improvements. • Strong communication and stakeholder management skills, with the ability to collaborate across business, application, data, infrastructure, platform, and security teams. • High level of ownership, curiosity, enthusiasm, and willingness to get hands-on with technical details. • Comfortable working in a fast-paced environment with evolving requirements and ambiguity. • Pragmatic delivery mindset, with a focus on building reliable and useful solutions rather than over-engineering. Nice to Have: • Experience with DeepAgent or similar agent frameworks. • Experience with Langfuse, Elastic, or similar observability/search platforms. • Experience using Redis for caching, conversation state, rate limiting, or queue-backed workflows. • Experience with vLLM or similar inference-serving frameworks for open-weight models. • Experience deploying GenAI workloads across cloud or containerised environments. • Experience in financial services or banking is not required.