GenAI Application Engineer (LLM / RAG / Agentic AI)

Client: Bank Sector Client Located In Singapore

LLM / RAG / Agentic AI / LangGraph / LangChain

Role Overview

We are looking for a Senior GenAI Application Engineer to design, build and deliver production-grade Generative AI (GenAI) and Large Language Model (LLM) applications for enterprise environments.

This is a hands-on GenAI application engineering / software engineering role focused on building real-world AI applications rather than pure AI research or prompt engineering.

You will work across LLM application development, Retrieval-Augmented Generation (RAG), Agentic AI, AI agents, LangGraph/LangChain orchestration, backend engineering, enterprise APIs and production deployment.

The successful candidate should have strong software engineering fundamentals and practical experience taking GenAI / LLM applications from prototype or Proof of Concept (POC) into production.

Banking or financial services experience is not required.

Key Responsibilities

Design, develop and enhance production-grade GenAI / LLM applications used by enterprise users.

Build Agentic AI / AI Agent workflows using frameworks such as LangGraph, LangChain or similar LLM orchestration frameworks.

Develop Retrieval-Augmented Generation (RAG) solutions including retrieval workflows, context management and prompt orchestration.

Build applications involving:

Large Language Models ( LLMs )

Retrieval-Augmented Generation ( RAG )

AI Agents / Agentic AI

Tool calling / function calling

Prompt orchestration

Context management

Integrate LLM applications with enterprise systems, REST APIs, backend services, databases, enterprise data sources and operational platforms.

Work with both open-weight / open-source models and hosted LLM services.

Support model integration and LLM inference / model-serving architectures.

Develop reliable backend services using Python, Java or similar programming languages.

Design scalable APIs and services for enterprise GenAI applications.

Implement production engineering practices including:

Logging

Monitoring

Distributed tracing

LLM observability

Evaluation / LLM evaluation

Error handling

Fallback mechanisms

Debugging and troubleshooting

Deploy and support GenAI applications within containerized environments such as Kubernetes or OpenShift.

Work closely with application, data, platform, infrastructure, DevOps, security and business teams.

Review technical designs, identify weaknesses and recommend practical improvements.

Ensure solutions are scalable, reliable, maintainable, observable and production-ready.

Key Requirements

Software Engineering

6+ years of software engineering experience, preferably with recent hands-on experience developing GenAI / LLM applications.

Strong backend software development experience using Python, Java or similar languages.

Strong understanding of:

REST APIs / API development

Backend services

Distributed systems

Enterprise application integration

Scalability and resilience

Production application architecture

Ability to write clean, maintainable and testable production code.

Generative AI / LLM Engineering

Proven hands-on experience building and deploying production-grade Generative AI applications, beyond simple prototypes, demos or hackathons.

Strong practical knowledge of:

Generative AI / GenAI

Large Language Models (LLMs)

LangGraph

LangChain

Retrieval-Augmented Generation (RAG)

Agentic AI

AI Agents / Agent workflows

LLM orchestration

Tool calling / function calling

Prompt engineering / prompt orchestration

Context management

LLM application integration

Candidates should understand how these technologies are used together to build reliable enterprise AI applications.

Production GenAI Engineering

Experience implementing production engineering practices for GenAI or backend applications, including:

LLM observability

Logging and monitoring

Distributed tracing

LLM / application evaluation

Failure handling

Fallback mechanisms

Debugging and troubleshooting

Application reliability

Performance and scalability

Experience taking AI applications from POC / prototype through production deployment is particularly important.

Open-Weight Models & Model Serving

Experience working with or integrating:

Open-weight models / open-source LLMs

Hosted LLM APIs

Model-serving platforms

LLM inference services

Hands-on exposure to vLLM or similar LLM inference / model-serving frameworks would be advantageous.

Cloud / Containers / Platform Engineering

Familiarity with production deployment environments such as:

Kubernetes

OpenShift

Containerized application deployment

Cloud or enterprise infrastructure environments

Candidates should be comfortable collaborating with DevOps, platform, infrastructure and security teams when deploying GenAI applications.

Nice to Have

Experience with one or more of the following would be advantageous:

Langfuse or similar LLM observability platforms

Elastic / Elasticsearch

Redis

vLLM

DeepAgent or similar Agentic AI frameworks

Cloud-based GenAI deployments

LLM model serving / inference

Caching and conversation-state management

Queue-backed AI workflows

Low-latency GenAI application architectures

What We Are Looking For

The ideal candidate is a hands-on software engineer who has moved into Generative AI application development, rather than someone focused purely on AI research or prompt engineering.

You should be able to:

Build real enterprise GenAI applications

Design reliable RAG and Agentic AI architectures

Integrate LLMs with APIs and enterprise systems

Write production-quality backend code

Diagnose complex technical problems

Challenge weak technical designs

Work across application, data, platform, infrastructure and security teams

Balance engineering quality with pragmatic delivery

We value engineers who are curious, practical, delivery-focused and willing to work hands-on with the technology.

Core Technical Skills / Search Keywords

Generative AI (GenAI),Large Language Models (LLM),LLM Applications,GenAI Application Engineering,Agentic AI,AI Agents,Lang