AI Application Engineer

AZTECH TECHNOLOGIES PTE LTD; Singapore; On-site; SGD 120,000 - 180,000; Full time

Job summary

AZTECH TECHNOLOGIES PTE LTD in Singapore is seeking an AI Application Engineer to translate business problems into production-ready LLM applications. You will design the application logic around the model: prompt architecture, context management, tool calling, RAG workflows, structured outputs, evaluation loops, and user-facing behavior.

You will build AI solutions such as knowledge assistants, document analyzers, and workflow copilots, and implement guardrails, evaluation loops, and user-facing

Qualifications

• Strong Python or TypeScript development skills.
• Hands-on experience with LLM APIs and structured outputs.
• Practical understanding of prompt design and retrieval augmentation.

Responsibilities

• Build AI applications such as knowledge assistants and document analyzers.
• Design prompt systems, retrieval flows, tool calls, and memory.
• Integrate LLM APIs and embedding/vision models with guardrails.
• Create reusable AI workflow patterns for summarization and classification.
• Implement evaluation loops and eligibility checks for high-impact actions.
• Develop testing data and scoring methods for answer quality and latency.
• Collaborate with business users to shape AI product flows with acceptance criteria.

Skills

Python

TypeScript

LLM APIs

Prompt design

Retrieval augmentation

Output validation

Debugging model

Ship usable apps

Tools

LangChain

LlamaIndex

Semantic Kernel

Pydantic

Ollama

Job description

AI Application Engineer

Role Mission

Own the translation of business problems into production-ready LLM applications. This role designs the application logic around the model: prompt architecture, context management, tool calling, RAG workflows, structured outputs, evaluation loops, and user-facing behavior.

Core Responsibilities

• Build AI applications such as knowledge assistants, document analyzers, email/thread analyzers, recruiting assistants, workflow copilots, and operational decision-support tools.
• Design prompt systems, model instructions, retrieval flows, tool calls, conversation memory, and structured output schemas.
• Integrate cloud and local LLM APIs, OpenAI-compatible endpoints, embedding models, vision models, and rerankers.
• Create reusable AI workflow patterns for summarization, extraction, classification, reasoning support, report generation, and human review.
• Implement guardrails for reliability, source attribution, schema validation, fallback behavior, and user confirmation before high-impact actions.
• Build evaluation sets and scoring methods to measure answer quality, hallucination risk, retrieval relevance, latency, and cost.
• Work with business users to turn vague automation ideas into specific AI product flows with measurable acceptance criteria.

Required Qualifications

• Strong Python or TypeScript development skills.
• Hands-on experience building with LLM APIs, chat completions, structured outputs, function/tool calling, or agent workflows.
• Practical understanding of prompt design, context windows, token limits, retrieval augmentation, and output validation.
• Ability to ship usable applications, not only prototypes or notebooks.
• Comfortable debugging model behavior and separating application bugs from model limitations.

Nice-to-Have Experience

• Experience with LangChain, LlamaIndex, Semantic Kernel, instructor, Pydantic, or similar frameworks.
• Experience with multimodal applications involving images, OCR, audio, or document understanding.
• Experience with enterprise knowledge assistants, HR tools, operations automation, customer support, or internal productivity software.
• Familiarity with local LLM deployment tools such as Ollama, LM Studio, vLLM, TGI, or llama.cp