Generative AI Engineer / LLM Engineer / AI Application Developer

Agency Growth Team; Singapore; On-site; SGD 90,000 - 150,000; Full time

Job summary

Agency Growth Team is seeking engineers to design, build, and maintain software applications that leverage generative AI, LLMs, and related ML tech. You will collaborate with product managers, designers, and engineers to understand user needs, define AI use cases, and translate requirements into reliable features.

You will develop components that connect models to business data, tools, and existing systems, including prompt design, RAG, embeddings, vector databases, model APIs, and

Qualifications

• Bachelor’s degree or equivalent practical experience in a related field
• Experience building and maintaining software applications, APIs, or data-driven products
• Proficiency in Python, JavaScript, TypeScript, or Java
• Familiarity with LLMs, model APIs, prompt design, and AI system strengths/limits
• Understanding of RAG, embeddings, semantic search, and vector databases
• Experience with version control, testing, deployment, and monitoring
• Ability to assess AI output quality with clear criteria and examples
• Familiarity with cloud platforms, containers, databases, and application security
• Strong problem-solving and ability to translate requirements into solutions
• Clear communication to explain technical trade-offs to non-specialists
• Commitment to privacy, security, data quality, and responsible AI use
• Experience deploying or supporting ML/LLM systems is a plus
• Relevant certifications or a portfolio may be considered an asset

Responsibilities

• Designs, builds, and maintains software using generative AI and LLM tech
• Works with PMs, designers, engineers to turn requirements into features
• Develops components connecting models to data, tools, and systems
• Evaluates performance, investigates issues, and improves prompts and config
• Documents system behavior and maintains performance and reliability after release

Skills

Python

JavaScript

TypeScript

Java

LLMs

RAG

Embeddings

Vector databases

APIs

Monitoring

Education

Bachelor’s degree in computer science, software engineering, data science, or related field

Tools

Model APIs

Vector databases

APIs

Cloud platforms

Job description

Designs, builds, and maintains software applications that use generative AI, large language models (LLMs), and related machine learning technologies. Works with product managers, designers, engineers, and subject matter experts to understand user needs, define suitable AI use cases, and turn requirements into reliable application features. Solutions may include chat assistants, document search and summarization, content generation, workflow automation, or AI-powered integrations.

Develops application components that connect models to business data, tools, and existing systems. This may involve prompt design, retrieval-augmented generation (RAG), embeddings, vector databases, model APIs, and agent or workflow orchestration. Selects and integrates appropriate models based on requirements for quality, latency, cost, privacy, and deployment constraints. Builds supporting software such as data-processing pipelines, APIs, user interfaces, and monitoring systems.

Evaluates model and application performance using representative test cases and user feedback. Investigates issues such as inaccurate or unsupported responses, inconsistent behavior, latency, and unexpected outputs, then improves prompts, retrieval, model configuration, or application logic. Helps establish safeguards for sensitive data, harmful outputs, access control, and appropriate use. Documents system behavior and limitations, monitors applications after release, and works with engineering and operations teams to maintain performance and reliability.

Role Description

Designs, builds, and maintains software applications that use generative AI, large language models (LLMs), and related machine learning technologies. Works with product managers, designers, engineers, and subject matter experts to understand user needs, define suitable AI use cases, and turn requirements into reliable application features. Solutions may include chat assistants, document search and summarization, content generation, workflow automation, or AI-powered integrations.

Develops application components that connect models to business data, tools, and existing systems. This may involve prompt design, retrieval-augmented generation (RAG), embeddings, vector databases, model APIs, and agent or workflow orchestration. Selects and integrates appropriate models based on requirements for quality, latency, cost, privacy, and deployment constraints. Builds supporting software such as data-processing pipelines, APIs, user interfaces, and monitoring systems.

Evaluates model and application performance using representative test cases and user feedback. Investigates issues such as inaccurate or unsupported responses, inconsistent behavior, latency, and unexpected outputs, then improves prompts, retrieval, model configuration, or application logic. Helps establish safeguards for sensitive data, harmful outputs, access control, and appropriate use. Documents system behavior and limitations, monitors applications after release, and works with engineering and operations teams to maintain performance and reliability.

Qualifications

• Bachelor’s degree in computer science, software engineering, data science, or a related field, or equivalent practical experience
• Experience building and maintaining software applications, APIs, or data-driven products
• Proficiency in one or more programming languages commonly used for AI applications, such as Python, JavaScript, TypeScript, or Java
• Familiarity with LLMs, model APIs, prompt design, and the strengths and limitations of generative AI systems
• Understanding of RAG, embeddings, semantic search, vector databases, or other methods for connecting models to external information
• Experience with software development practices such as version control, testing, code review, deployment, and monitoring
• Ability to assess AI output quality and design evaluations using clear criteria and representative examples
• Familiarity with cloud platforms, containers, databases, and application security is an asset
• Strong problem-solving skills and the ability to turn product or business requirements into practical technical solutions
• Clear communication skills and the ability to explain technical trade-offs to non-specialists
• Careful approach to privacy, security, data quality, and responsible AI use
• Experience deploying or supporting machine-learning or LLM-powered systems in production is an asset
• Relevant certifications, advanced study, or a portfolio of AI application projects may be considered an asset