Full Stack AI Engineer

Resource Services Group X Pty Ltd; Kuala Lumpur; Hybrid; MYR 180,000 - 320,000; Full time

Benefits offered by this job

Hybrid working arrangements in Kuala L

Job summary

Resource Services Group X Pty Ltd in Kuala Lumpur is seeking a Full Stack AI Engineer to design, build, and operate production AI-powered applications. You will own features end-to-end, from requirements through deployment, with a focus on reliability, observability, and cost efficiency.

Join a team that blends frontend and backend work with LLMs, RAG, and secure cloud deployment. Hybrid work in Kuala Lumpur is offered.

Qualifications

• Bachelor's degree in CS, SE, or related field.
• 8–10 years of software development in production.
• Hands-on Azure experience including AI services.

Responsibilities

• Design and build LLM-powered applications with a focus on production readiness.
• Build and optimize RAG pipelines and embedding models.
• Develop AI agents and multi-agent systems with LangChain or similar.
• Implement system-level prompt engineering and guardrails.
• Collaborate with product and business teams to ship scalable AI features.
• Ensure observability, reliability, and security in deployments.

Skills

AI/LLM engineering

Full stack development

Python

Node.js

React/Next.js

Azure

DevOps

Education

Bachelor's degree in Computer Science or related

Tools

Azure OpenAI

LangChain

Kubernetes

Docker

PostgreSQL

Job description

About the Role

We are looking for a Full Stack AI Engineer to design, build, and operate AI-powered applications that solve real business problems — in production, not demos. This role combines production-grade software engineering with modern AI capabilities: LLMs, RAG pipelines, AI agents, and secure cloud deployment. You will own features end-to-end, from requirements gathering and architecture through to deployment, monitoring, and iteration. You will work closely with product teams, business stakeholders, and developers to ship AI solutions that are reliable, observable, cost-efficient, and secure. This is a production engineering role. If something you build fails at 2am, you understand why — and you have already built the observability to detect it earlier next time.

What You'll Do

AI & LLM Engineering

• Design and build LLM-powered applications using models such as Claude, GPT-4, Gemini, or open-source equivalents (Llama, Mistral), selecting the right model based on latency, cost, and quality tradeoffs.
• Build and optimise RAG pipelines connecting LLMs to enterprise knowledge sources; own chunking strategy, retrieval quality, and embedding model selection.
• Develop AI agents and multi-agent systems using frameworks such as LangChain, LangGraph, CrewAI, or LlamaIndex; design for the failure modes specific to agentic workflows.
• Build evaluation harnesses that measure output quality, faithfulness, hallucination rate, latency, and cost across model versions and prompt changes — governing whether AI features ship or roll back.
• Implement prompt engineering at the system level, including guardrails, output filtering, and red-teaming to ensure safe and reliable AI behaviour.
• Integrate workflow automation platforms (e.g. n8n, Make, Power Automate) to extend AI capabilities into business operations.

Full Stack Development

• End-to-End Delivery: Build and maintain high-performance full-stack applications, coupling responsive front-ends (React/Next.js) with production-grade backend services.
• Backend Architecture: Design, build, and operate robust microservices and APIs using Python (FastAPI/Django) or Node.js, strictly adhering to clean architecture principles.
• API Design & Identity: Architect secure RESTful and GraphQL APIs. Implement OAuth 2.0, JWT (including rotation and revocation strategies), robust session management, and Role-Based Access Control (RBAC).
• Database Engineering: Design and optimise PostgreSQL schemas for high-throughput workloads. Drive strategies for normalization, indexing, query optimisation, migrations, connection pooling, and read-replicas/partitioning.
• Asynchronous Systems: Build event-driven architectures leveraging queues, pub/sub messaging, and background workers to decouple services and ensure seamless scalability.

Cloud, DevOps & Mass-Scale Deployment

• Cloud Infrastructure: Deploy and operate production services on Microsoft Azure (essential), with AWS or GCP experience considered highly advantageous.
• Compute Strategy: Architect scalable serverless solutions (Azure Functions, AWS Lambda) alongside containerised workloads, deliberately selecting the optimal compute model per task.
• Container Orchestration: Manage Docker and Kubernetes environments, handling deployments, autoscaling (HPA/VPA), service mesh integration, and advanced release strategies (rolling, blue-green, canary).
• Infrastructure as Code: Provision and version cloud environments repeatably across dev, test, and production utilizing Terraform or Bicep.
• High Availability & Scale: Architect for mass-scale resilience. Ensure multi-region failover, sophisticated load balancing, auto-scaling under variable load, zero-downtime deployments, and robust capacity planning.
• CI/CD & Observability: Build automated deployment pipelines with embedded testing, security scanning, and secrets management. Own production reliability through comprehensive tracing, alerting, and root-cause incident response.

Security & Authentication

• Zero-Trust Identity: Drive end-to-end authentication and authorization (OAuth 2.0/OIDC, JWT), enforcing secure session handling, RBAC/ABAC, and strict secrets management.
• Proactive Security: Conduct threat modelling and secure code reviews. Integrate SAST/DAST tooling into CI/CD pipelines to intercept vulnerabilities prior to deployment.
• Data Protection: Implement robust encryption at rest and in transit, securing data storage and enforcing stringent access controls across all databases and services.
• Application Hardening: Apply OWASP Top 10 principles across the entire stack, fortifying APIs against common attack vectors such as injection, broken authentication, and excessive data exposure.

AI & Emerging Tech (Advantageous, not essential)

• AI Integration: Leverage LLM-powered applications and AI agent frameworks (e.g., LangChain, LangGraph) to enhance platform capabilities.
• Strategic Alignment: Integrate AI- adjacent services seamlessly into the broader architecture to support and accelerate RSGx's internal AI programme.

Collaboration & Delivery

• Technical Scoping: Translate complex stakeholder requirements into elegant technical solutions. Constructively push back when proposed approaches add complexity without delivering tangible business value.
• Cross-Functional Execution: Collaborate seamlessly across product, data, and business teams to consistently deliver projects on time.
• Engineering Leadership: Mentor peers, conduct rigorous code reviews, and actively contribute to elevating the team's engineering standards and best practices.

What We're Looking For Education & Experience

• Bachelor's Degree in Computer Science, Software Engineering, Data Science, or a related field.
• 8-10 years of software development experience in a production environment.
• Demonstrable hands-on experience with Microsoft Azure — including compute, networking, IAM, and Azure-native AI services (Azure OpenAI, Azure ML, Azure AI Foundry).
• 1+ year of hands-on experience building and deploying AI/LLM applications.

Technical Skills — Core

• Experience building and operating AI agent and multi-agent systems.
• Experience integrating AI into enterprise applications at scale.
• Knowledge of MLOps practices: model versioning, monitoring, drift detection.
• Deep experience with Azure AI services: Azure OpenAI Service, Azure Machine Learning, Azure AI Foundry, and Azure Cognitive Services.
• Familiarity with workflow automation tools: n8n, Make, Zapier, or Power Automate.
• Exposure to data engineering and ETL pipelines.
• Familiarity with AI safety practices: output guardrails, adversarial testing, LLM-as-judge evaluation.

What Strong Candidates Demonstrate

• Describe a specific production failure in an AI system they owned — the failure mode, and what they built to prevent it recurring.
• Walk through a RAG pipeline they shipped: retrieval quality before and after a meaningful improvement, and the metric used to measure it.
• Articulate when not to use an LLM — and what simpler approach they chose instead.
• Explain a security decision they made in an API or cloud deployment: the threat they were mitigating and why they chose that control.

What We Offer

• Direct involvement in enterprise AI implementations, from architecture to production.
• Exposure to a modern AI stack across multiple cloud platforms and LLM providers.
• Collaborative team environment with meaningful technical ownership.
• Hybrid working arrangements in Kuala Lumpur.
• Clear career growth path in a discipline with strong market demand.