New opportunity

Junior AI Engineer (Assurance/ 1 year contract)

Certis Group · Singapore

About this role

The Junior AI Engineer will be responsible for developing and enhancing AI-powered applications, automation solutions, and digital tools to support business processes. This role involves designing, building, testing, and maintaining full-stack applications while integrating AI technologies, APIs, and databases to improve productivity. Responsibilities: - Design and maintain full-stack applications using modern frameworks. - Implement and optimize solutions involving LLMs, intelligent document processing, and retrieval systems. - Collaborate with stakeholders to translate business needs into technical solutions. - Troubleshoot technical issues, conduct testing, and support deployment activities. - Create and maintain technical documentation and implementation guidelines. - Participate in project planning and cross-functional collaboration. Requirements: - Bachelor's Degree in Computer Science, Software Engineering, Information Systems, Data Science, Artificial Intelligence, or a related discipline. - 1 to 3 years of experience in software engineering, AI development, or full-stack development. - Hands-on experience building and deploying applications or internal business tools. - Familiarity with AI and machine learning concepts, including prompt engineering, LLM integrations, and retrieval-based systems. - Proficiency in full-stack technologies such as React, Next.js, Node.js, Python, FastAPI, or Django. - Experience with APIs, databases, version control, and cloud-based deployment. - Strong analytical, problem-solving, and communication skills.

For full details about this role, click “Apply on company site” to view the employer’s original posting.

Skills for this role

Software EngineeringAI DevelopmentFull-stack DevelopmentPrompt EngineeringLLM IntegrationRetrieval-based systemsIntelligent AutomationReactNext.jsNode.jsPythonFastAPIDjangoAPI DevelopmentDatabase ManagementVersion ControlCloud Deployment

Checking your profile…

Preparation suggestions, not the employer’s actual interview questions. Always check the original posting for current requirements.

Understand the role

What matters most

Full-Stack AI Application Development
The role requires designing, building, and maintaining end-to-end applications that integrate AI technologies with frontend and backend frameworks. You must demonstrate proficiency in modern stacks like React, Next.js, Python, and FastAPI to deliver functional business tools.
AI Integration and Optimization
A core priority is implementing and refining LLM-based solutions, including intelligent document processing and retrieval systems. You will be expected to optimize these workflows to improve productivity and user experience within the organization.
Stakeholder Collaboration and Documentation
You must translate business requirements into technical solutions while maintaining clear documentation and implementation guidelines. Success depends on your ability to communicate technical progress to stakeholders and collaborate across functions.

Likely challenges to think through

Balancing Rapid Development with System Stability
As a contract role focused on automation and AI tools, there is a risk of pressure to deliver features quickly. You must prepare to demonstrate how you maintain high code quality, testing standards, and documentation while working in a fast-paced environment.
Bridging Technical AI Concepts with Business Needs
Translating complex AI capabilities like retrieval-based systems into practical business process improvements can be difficult. Prepare by practicing how you explain technical trade-offs and AI limitations to non-technical stakeholders to ensure project alignment.

Practice your answers

Technical practice

Full-stack integration of LLMs

What to coverExplain how you would integrate an LLM into a web application using Python and a framework like FastAPI. Discuss the architecture for handling asynchronous requests and managing API latency when interacting with external AI models.

Retrieval-Augmented Generation (RAG) fundamentals

What to coverDescribe the components required to build a retrieval-based system for document processing. Focus on the role of vector databases, embedding models, and how you ensure the retrieved context is relevant to the user's query.

Prompt engineering strategies

What to coverDiscuss techniques for optimizing prompts to improve the accuracy and consistency of LLM outputs. Mention methods like few-shot prompting, chain-of-thought, or system-level instructions to constrain model behavior.

Frontend and backend state management

What to coverGiven the requirement for React and Next.js, explain how you manage state between the frontend and a Python-based backend. Suggest how to handle real-time updates or long-running AI tasks in the UI.

API design and security

What to coverHow do you approach designing secure APIs for internal business tools? Address authentication, rate limiting, and the importance of validating inputs when connecting to AI services.

Testing and debugging AI applications

What to coverWhat is your approach to testing applications that rely on non-deterministic AI outputs? Suggest strategies for unit testing code versus evaluating the quality of AI-generated responses.

Database selection for AI tools

What to coverCompare the use of relational databases versus vector databases in the context of building AI-powered applications. Explain when you would choose one over the other for storing application data versus embedding vectors.

Deployment and CI/CD

What to coverDescribe your experience with cloud-based deployment environments. Suggest a basic CI/CD pipeline structure for a full-stack application that includes automated testing and version control.

Behavioural practice

Translating business needs to technical solutions

What to coverDescribe a time you had to gather requirements from a non-technical stakeholder. Explain how you translated their business objective into a functional technical specification or feature set.

Handling technical ambiguity

What to coverShare an example of a project where the requirements were unclear or changed mid-development. How did you manage the situation to ensure the final output still met the core business goals?

Collaboration in cross-functional teams

What to coverProvide an example of working with a team member from a different discipline (e.g., design or operations). How did you ensure effective communication and alignment on project deliverables?

Continuous learning and adaptation

What to coverThe AI field evolves rapidly; describe a recent technology or framework you learned on your own. How did you apply this new knowledge to improve a project or process?

Sharpen your knowledge

Topics to prepare

Retrieval-Augmented Generation (RAG) Architecture
Review the conceptual flow of RAG systems, specifically how data is indexed, retrieved, and passed to an LLM. Exercise: Sketch a diagram showing the interaction between a vector database, an embedding model, and an LLM to explain how you would build a document-processing tool for business automation.
Full-Stack Application Lifecycle
Understand the integration points between frontend frameworks like React/Next.js and backend services like FastAPI/Django. Exercise: Outline a plan for a simple internal tool that takes user input, processes it via an LLM API, and displays the result, focusing on error handling and state management.

Skills to revise

Prompt Engineering for Business Automation
Practice designing system prompts that enforce specific output formats (e.g., JSON) for intelligent document processing. Exercise: Create a set of prompts to extract structured data from unstructured business documents, testing for consistency and accuracy.
API Integration and Backend Development
Develop proficiency in connecting Python-based backends to external AI services. Exercise: Build a small FastAPI endpoint that consumes an OpenAI or similar LLM API, including basic input validation and logging for troubleshooting.
Version Control and Deployment Workflows
Demonstrate familiarity with Git and cloud deployment practices. Exercise: Create a repository for a mock project, implement a basic CI/CD pipeline configuration, and document the steps required to deploy a containerized application to a cloud environment.

Your preparation checklist

Prepare a full-stack AI project walkthrough
Select a past project that demonstrates your ability to integrate an LLM or retrieval system into a web application. Prepare to explain your choice of stack (e.g., React/Next.js with Python/FastAPI), how you handled API integrations, and the specific steps taken to ensure the application was testable and maintainable.
Document your experience with RAG and LLM workflows
Create a concise summary of your hands-on experience with retrieval-based systems or intelligent document processing. Be ready to discuss how you optimized prompts or managed data retrieval to improve the accuracy and performance of an AI-driven tool.
Review software development lifecycle best practices
Prepare examples of how you have managed version control, conducted testing, and handled deployment in a cloud environment. Be ready to explain your approach to documenting code and implementation guidelines for internal business tools.
Formulate questions for the interviewers
Prepare thoughtful questions regarding the team's current AI development pipeline, how they prioritize business requirements for automation projects, and the specific technical challenges they face when integrating AI into their existing operational workflows.

Availability last checked: 18 Oct 2026. Status can change after a check; confirm on the employer’s website. Report an issue · Our checking policy

KEEP EXPLORING

Similar AI jobs

Related skills and specializations in Singapore. Matched to this role, not your profile.

Explore more jobs

Finding similar opportunities…