Senior Generative AI Application Engineer_ Contract

Job title: Senior Generative AI Application Engineer

Position level: Professional / Senior Executive

Employment type: Contract, Contract duration: 12 months renewable

Working location: Singapore CBD in 2026; PDD from 2027

Our client is a leading bank in Asia with an established international network across Asia Pacific, Europe and North America.

This is a hands-on engineering position operating at the intersection of software engineering, Generative AI application development, enterprise integration and production delivery.

This is not a pure research, data science or prompt-engineering-only role. The successful candidates will design, build, deploy and enhance production-grade GenAI applications that are reliable, observable, secure, maintainable and useful to enterprise users.

Key Responsibilities

Design, develop and enhance production-grade Generative AI applications.

Build GenAI solutions using LangGraph, LangChain or comparable orchestration frameworks.

Develop retrieval-augmented generation pipelines, agentic workflows, tool-calling capabilities, prompt orchestration and context-management solutions.

Integrate hosted and open-weight large language models into enterprise applications.

Connect GenAI applications with APIs, backend services, databases, document repositories, enterprise data sources and operational platforms.

Build reliable backend services using Python, Java or comparable programming languages.

Design and implement model-routing, retrieval, caching, conversation-state and fallback mechanisms.

Establish application logging, tracing, monitoring, evaluation and troubleshooting capabilities.

Develop automated evaluation frameworks to measure retrieval quality, response accuracy, reliability and application performance.

Deploy and operate GenAI workloads within Kubernetes, OpenShift or similar containerised environments.

Apply appropriate security, access-control and data-protection measures to enterprise AI solutions.

Troubleshoot complex application, model, integration and infrastructure issues.

Write clean, maintainable, reusable and testable production code.

Review technical designs, challenge unsuitable approaches and recommend practical improvements.

Collaborate with business, application, data, platform, infrastructure, architecture and cybersecurity teams.

Support applications through development, testing, deployment, production stabilisation and continuous improvement.

Requirements

At least 5 years of software engineering, application development or closely related technical experience.

Recent hands-on experience designing and building Generative AI applications.

Proven experience delivering production-grade GenAI applications—not only demonstrations, proofs of concept or academic projects.

Strong practical experience with LangGraph, LangChain or comparable LLM orchestration frameworks.

Hands-on experience with RAG, agentic workflows, tool calling, prompt orchestration and context management.

Experience integrating LLMs with real applications through APIs, backend services and enterprise data sources.

Strong backend engineering skills using Python, Java or similar languages.

Good understanding of REST APIs, distributed systems and production-resilience patterns.

Experience designing retrieval pipelines involving document parsing, chunking, embeddings, vector search, reranking and cited generation.

Practical experience with observability, logging, tracing, evaluation and troubleshooting for GenAI or backend applications.

Familiarity with Docker and container orchestration platforms such as Kubernetes or OpenShift.

Understanding of application security, access controls and responsible handling of enterprise information.

Strong analytical, debugging and problem-solving capabilities.

Ability to work effectively with incomplete information and evolving requirements.

Strong ownership, curiosity and genuine interest in building useful AI products.

Good communication skills and the confidence to challenge weak technical designs.

Ability to coordinate effectively across business and multidisciplinary technology teams.

Banking or financial-services experience is advantageous but not mandatory. Strong GenAI application engineering and practical production-delivery experience are more important.

Good-to-Have Experience

Open-weight models such as Llama, Mistral, Qwen or comparable models.

vLLM or similar model inference and serving frameworks.

DeepAgent or comparable agent frameworks.

Langfuse or similar LLM observability and evaluation platforms.

Elasticsearch or similar enterprise search technologies.

Redis for caching, conversation state, rate limiting, pub/sub or queue-backed workflows.

Vector databases and hybrid retrieval approaches.

Model Context Protocol integrations.

Cloud-based GenAI services and deployment platforms.

CI/CD pipelines for AI and backend applications.

Interested candidates are kindly requested to email their CV with their experience to  sandeep.sringeripai@global.ntt

We look forward to your application!