Senior GenAI Application Engineer

optimum solutions (singapore) pte ltd; Singapore; On-site; SGD 120,000 - 180,000; Full time

Job summary

Optimum Solutions (Singapore) Pte Ltd is seeking a Senior GenAI Application Engineer to design, build and deliver production-grade GenAI applications for enterprise use cases. The ideal candidate will work at the intersection of software engineering, GenAI application development, enterprise integration, data, and platform engineering.

This is a hands‑on engineering role requiring practical experience with LangGraph, LangChain, RAG, agentic workflows, tool calling, LLM integration, APIs, and

Qualifications

• 6+ years of software engineering experience with GenAI or AI-powered apps.
• Proven production-grade GenAI app development experience.
• Hands-on with LangGraph/LangChain and orchestration workflows.

Responsibilities

• Design and develop production-grade GenAI applications using Python, Java, or similar technologies.
• Build agentic workflows with LangGraph/LangChain for multi-step reasoning and automation.
• Develop and optimize RAG solutions including ingestion, embeddings, and retrieval.
• Integrate LLMs into enterprise apps via hosted APIs, databases, and enterprise data sources.
• Implement tool calling and prompt orchestration for reliable enterprise interactions.
• Engineer production reliability with error handling, retries, timeouts and caching.
• Build observability: logging, tracing, latency monitoring and token usage tracking.
• Containerize and deploy GenAI apps with Docker, Kubernetes, OpenShift, in cloud platforms.
• Collaborate across teams to meet enterprise architecture, security, and ops needs.
• Challenge weak designs and push for scalable, maintainable solutions.

Skills

Backend development

API design

Distributed systems

Observability & monitoring

Production-grade AI applications

Tools

LangGraph

LangChain

RAG

Agentic workflows

Tool calling

Prompt orchestration

Docker

Kubernetes/OpenShift

Cloud platforms

Job description

Job Description

We are looking for a Senior GenAI Application Engineer to design, build, and deliver production-grade Generative AI applications for enterprise use cases. The ideal candidate will work at the intersection of software engineering, GenAI application development, enterprise integration, data, and platform engineering.

This is a hands‑on engineering role requiring practical experience with LangGraph, LangChain, RAG, agentic workflows, tool calling, LLM integration, APIs, and enterprise systems. The successful candidate will have strong engineering judgment and a pragmatic approach to building AI solutions that are reliable, observable, maintainable, secure, and scalable.

Key Responsibilities

1. Design and develop production-grade GenAI applications using Python, Java, or similar backend technologies and modern AI application frameworks.

2. Build agentic workflows using frameworks such as LangGraph, LangChain, or similar orchestration technologies to support multi-step reasoning, tool usage, and workflow automation.

3. Develop and optimize RAG solutions, including document ingestion, chunking, embeddings, retrieval, reranking, context management, and grounded response generation.

4. Integrate LLMs into enterprise applications using hosted LLM APIs, open-weight models, backend services, enterprise APIs, databases, and other organizational data sources.

5. Implement tool calling and prompt orchestration to enable AI applications to interact reliably with enterprise systems, APIs, databases, and operational platforms.

6. Engineer applications for production reliability, including error handling, retries, fallbacks, timeouts, rate limiting, caching, state management, and graceful degradation.

7. Build observability and evaluation capabilities for GenAI applications, including structured logging, tracing, latency monitoring, token usage tracking, quality evaluation, and troubleshooting.

8. Containerize and deploy GenAI applications using technologies such as Docker, Kubernetes, OpenShift, and cloud-based infrastructure.

9. Collaborate across application, data, platform, infrastructure, security, and business teams to design solutions that meet enterprise architecture, security, and operational requirements.

10. Challenge weak technical designs and continuously improve solutions, balancing engineering quality, scalability, maintainability, delivery timelines, and business value without unnecessary over‑engineering.

Key Requirements

1. 6+ years of software engineering experience, with recent hands‑on experience developing Generative AI or AI-powered applications.

2. Proven experience building and supporting production-grade GenAI applications, beyond prototypes, proof‑of‑concepts, experiments, or demos.

3. Strong hands‑on experience with LangGraph, LangChain, or similar GenAI orchestration frameworks, including workflow design and state/context management.

4. Practical experience with RAG, agentic workflows, tool calling, prompt orchestration, context management, and LLM application patterns.

5. Strong backend development skills in Python, Java, or similar programming languages, with an emphasis on clean, maintainable, and testable code.

6. Experience integrating LLMs into real-world applications through APIs, microservices, backend systems, enterprise platforms, databases, and other data sources.

7. Understanding of open‑weight models and model‑serving patterns, with hands‑on experimentation or experience using technologies such as vLLM or similar inference‑serving frameworks.

8. Strong understanding of API design, distributed systems, and production resilience patterns, including retries, timeouts, circuit breakers, caching, asynchronous processing, and fault handling.

9. Experience with production observability and deployment, including logging, tracing, monitoring, troubleshooting, Docker, Kubernetes/OpenShift, and cloud or container platforms.