AI Application Engineer

K2 Partnering Solutions Pte Ltd; Singapore; On-site; SGD 120,000 - 180,000; Full time

Job summary

K2 Partnering Solutions Pte Ltd is seeking a hands-on AI Application Engineer to bridge rapid AI prototyping and production-grade software delivery in Singapore. You will refactor prototypes into secure, scalable, governed applications and collaborate with product owners, data engineers, security specialists, and business stakeholders.

You will re-architect prototypes into production-ready software using clean architecture, build end-to-end AI capabilities, and deploy via modern CI/CD pipelines.

Qualifications

• 7+ years of hands-on software development experience building and supporting enterprise-grade or cloud-native applications.
• Strong expertise in modern languages and frameworks such as React, TypeScript, Node.js, Python, .NET, or Java.
• Hands-on experience integrating applications with major cloud AI services (e.g., Azure OpenAI, Azure AI Search, Azure ML, or equivalent public cloud environments) and RESTful services.
• Practical experience implementing LLMs, RAG patterns, prompt engineering, vector search, embeddings, and workflow orchestration.
• Solid understanding of secure coding practices (secrets management, least-privilege access) and identity frameworks (OAuth 2.0, OpenID Connect, SAML, JWT, RBAC).
• Experience using CI/CD platforms (e.g., GitHub Actions, Azure DevOps), containerization, deployment rollbacks, and environment management.
• Firm grasp of AI-specific risks, including hallucinations, prompt injection, data leakage, and explainability limitations.

Responsibilities

• Re-architect early-stage AI prototypes and experimental code into production-ready software with clean architecture and robust APIs.
• Design and build end-to-end AI capabilities, including conversational interfaces and RAG architectures.
• Develop scalable applications across front-end UI, back-end APIs, and database integrations.
• Implement AI safety patterns, including prompt management, filtering, and audit logging.
• Develop reusable engineering playbooks and starter templates for AI delivery across teams.
• Build automated testing suites and system monitoring for latency, token usage, and costs.
• Collaborate with platform engineers to deploy applications via CI/CD pipelines and enterprise cloud infra.
• Maintain solution designs, SOPs, and support guides for long-term maintainability.

Skills

React

TypeScript

Node.js

Python

NET/Java

Azure OpenAI

LLM/RAG

CI/CD

Security best practices

OAuth/JWT

Tools

GitHub Actions

Azure DevOps

Docker

Kubernetes

REST APIs

Job description

We are seeking a hands-on AI Application Engineer to help bridge the gap between rapid AI prototyping and production-grade software delivery. In this role, you will help establish a structured path to production for high-potential AI use cases—transforming initial prototypes into secure, scalable, and fully governed applications.

Sitting within our core engineering division, you will collaborate with product owners, data engineers, security specialists, and business stakeholders to refactor, harden, and scale AI-driven solutions across the organization.

Key Responsibilities

• Re-architect early-stage AI prototypes and experimental code into maintainable, production-ready software using clean architecture, secure authentication, and robust APIs.
• Design and build end-to-end AI capabilities, including conversational interfaces, Retrieval-Augmented Generation (RAG) architectures, workflow agents, and enterprise automation tools.
• Build and maintain scalable applications across front-end UI, back-end APIs, database integrations, authentication, logging, and monitoring systems.
• Implement AI safety patterns, including retrieval grounding, prompt management, input/output filtering, audit logging, and human-in-the-loop workflows.
• Develop standardized starter templates, reusable patterns, and engineering playbooks to accelerate AI delivery across multiple teams.
• Build automated testing suites (functional, regression, prompt quality, and guardrail validation) and implement system monitoring for latency, token usage, cost, and error tracking.
• Partner with platform engineers to deploy applications via modern CI/CD pipelines, containerization standards, and enterprise cloud infrastructure.
• Maintain solution designs, standard operating procedures, and support guides to ensure long-term maintainability.

Required Qualifications

• 7+ years of hands-on software development experience building and supporting enterprise-grade or cloud-native applications.
• Strong expertise in modern languages and frameworks such as React, TypeScript, Node.js, Python, .NET, or Java.
• Hands-on experience integrating applications with major cloud AI services (e.g., Azure OpenAI, Azure AI Search, Azure ML, or equivalent public cloud environments) and RESTful services.
• Practical experience implementing LLMs, RAG patterns, prompt engineering, vector search, embeddings, and workflow orchestration.
• Solid understanding of secure coding practices (secrets management, least-privilege access) and identity frameworks (OAuth 2.0, OpenID Connect, SAML, JWT, RBAC).
• Experience using CI/CD platforms (e.g., GitHub Actions, Azure DevOps), containerization, deployment rollbacks, and environment management.
• Firm grasp of AI-specific risks, including hallucinations, prompt injection, data leakage, and explainability limitations.

Preferred Experience

• Experience with AI orchestration frameworks (e.g., LangChain, LlamaIndex, Semantic Kernel, AutoGen) and vector databases (e.g., pgvector, Pinecone).
• Exposure to AI evaluation, red teaming, and safety benchmarking.
• Experience integrating with enterprise collaboration platforms and workflow systems.
• Familiarity with public sector compliance, data classification, and regulatory frameworks.
• Practical use of AI-assisted development tools (e.g., GitHub Copilot) to improve engineering velocity.