AI Engineer

ES TECH CONSULTANCY PTE. LTD.; Singapore; On-site; SGD 120,000 - 180,000; Full time

Job summary

ES TECH CONSULTANCY PTE. LTD. seeks an AI Software Engineer (LLM, GenAI & Agentic Systems) to design, build, and deploy production-grade AI solutions leveraging LLMs, RAG, and agentic workflows.

You’ll work with solution architects, data scientists, product teams, and clients to translate AI concepts into scalable, secure, business-ready applications. You will shape responsible AI practices, implement safeguards, and ensure compliance across enterprise environments while integrating with OpenAI,

Qualifications

• Experience delivering AI applications, agentic systems, and RAG solutions for enterprise contexts.
• Proven ability to translate business requirements into scalable AI architectures.
• Strong software engineering practices and secure coding.

Responsibilities

• AI Solution Development: Design, develop, test, and deploy AI-enabled applications using LLMs, GenAI technologies, and automation frameworks.
• Integrate foundation models and AI services such as OpenAI, Azure OpenAI, Claude, Bedrock, Gemini, Vertex AI.
• Build AI-powered solutions including enterprise chatbots, RAG apps, knowledge management assistants, and AI copilots.
• Agentic Systems & Intelligent Automation: Design agent-based architectures, memory management, tool calling, and workflow orchestration.
• Retrieval-Augmented Generation (RAG) & Knowledge Systems: Design RAG architectures using embeddings and semantic search.
• AI-Assisted Software Engineering: Use AI tools like Copilot, Claude Code, Gemini Code Assist, Windsurf, and apply prompt engineering.
• Software Engineering & Integration: Develop APIs and integrations using Python; deploy with Docker.
• AI Quality, Evaluation & Responsible AI: Define eval frameworks, monitor guardrails, compliance.
• Deployment & Operations: Containerisation with Docker; collaborate with DevOps; observability and telemetry.
• Collaboration & Knowledge Sharing: Work with stakeholders, product managers, architects.

Skills

LLM

GenAI

Agentic Systems

RAG

Python

APIs

Docker

GitHub Copilot

AI Tools

Tools

OpenAI

Azure OpenAI

Anthropic Claude

Amazon Bedrock

Google Gemini

Vertex AI

Vector search

Job description

AI Engineer (LLM, GenAI & Agentic Systems)

The ideal candidate is an AI engineer who can build and deploy real-world LLM and GenAI solutions. Experience delivering AI applications, agentic systems, RAG solutions, and AI-assisted engineering practices will be weighted more heavily than frontend framework expertise.

About the Role

We are seeking a talented AI Software Engineer (LLM, GenAI & Agentic Systems) to join our growing AI Engineering team. This role focuses on designing, building, and deploying production-grade AI solutions that leverage Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), agentic workflows, and AI-assisted software engineering practices.

You will work closely with solution architects, product teams, data scientists, and clients to transform AI concepts into scalable, secure, and business-ready applications. Beyond writing high-quality software, you will play a key role in shaping how AI technologies are applied responsibly and effectively across enterprise environments.

Key Responsibilities

AI Solution Development

Design, develop, test, and deploy AI-enabled applications using Large Language Models (LLMs), Generative AI technologies, and intelligent automation frameworks.

Integrate foundation models and AI services such as OpenAI, Azure OpenAI, Anthropic Claude, Amazon Bedrock, Google Gemini, Vertex AI, or equivalent platforms.

Develop AI-powered solutions including:

• Enterprise chatbots and virtual assistants
• Retrieval-Augmented Generation (RAG) applications
• Intelligent document processing solutions
• Knowledge management assistants
• AI copilots and task automation agents
• Multi-agent and agentic workflow systems

Translate business requirements into scalable AI solution architectures.

Partner with stakeholders to prototype, demonstrate, and productionize AI capabilities.

Agentic Systems & Intelligent Automation

Design and implement agent-based architectures and workflow orchestration solutions.

Build systems that leverage tool/function calling, memory management, context engineering, and task planning.

Develop AI workflows that interact with enterprise applications, APIs, and knowledge repositories.

Evaluate and optimize agent performance for accuracy, reliability, latency, and operational efficiency.

Implement suitable safeguards and human-in-the-loop controls for critical business processes.

Retrieval-Augmented Generation (RAG) & Knowledge Systems

Design and implement RAG architectures using embeddings, semantic search, and retrieval pipelines.

Develop ingestion, indexing, retrieval, and ranking workflows for enterprise knowledge repositories.

Optimize retrieval quality, grounding accuracy, and response relevance.

Work with vector search technologies, retrieval architectures, and semantic indexing approaches.

Evaluate retrieval effectiveness using structured testing methodologies and performance metrics.

AI-Assisted Software Engineering

Utilize AI-assisted development tools such as GitHub Copilot, Cursor, Claude Code, Gemini Code Assist, Amazon Q Developer, JetBrains AI Assistant, Windsurf, or equivalent tools.

Apply prompt engineering and context management techniques to improve software development productivity.

Leverage AI tools for:

• Code generation
• Unit test generation
• Documentation
• Refactoring
• Code reviews
• Technical analysis

Critically review AI-generated outputs for correctness, maintainability, security, compliance, and performance.

Software Engineering & Integration

Develop applications, services, APIs, and automation components primarily using Python and related technologies.

Design and implement RESTful APIs and integrations with third-party platforms and enterprise systems.

Build reusable AI services, SDKs, and internal accelerators.

Apply software engineering best practices including version control, testing, code reviews, and documentation.

Participate in architecture reviews and technical design discussions.

AI Quality, Evaluation & Responsible AI

Define evaluation frameworks for AI applications and establish measurable quality criteria.

Use AI evaluation methodologies and tools to assess:

• Accuracy
• Grounding quality
• Hallucination rates
• Latency
• User satisfaction

Implement guardrails, monitoring, and governance controls to support responsible AI adoption.

Ensure compliance with organisational security, privacy, data protection, and intellectual property policies.

Promote ethical and responsible use of AI technologies.

Deployment & Operations

Package and deploy AI applications using containerisation technologies such as Docker.

Collaborate with DevOps teams to deploy AI services into cloud and enterprise environments.

Implement application logging, monitoring, observability, and AI performance telemetry.

Support production deployments and troubleshoot operational issues.

Collaboration & Knowledge Sharing

Work closely with business stakeholders, product managers, architects, and data s