Production AI Engineer: LLMs & Agentic Workflows

CodeRound; Hinoba-an; On-site; PHP 900,000 - 1,400,000; Full time

Job summary

CodeRound is seeking an AI Engineer in the Philippines to build production-grade AI applications using LLMs and agentic workflows. You will collaborate with product and engineering teams to develop scalable AI solutions, integrate models into real-world products, and optimize performance for enterprise use cases.

You will design backend services, deploy AI features, and continuously improve models through prompt engineering and testing, while staying ahead of GenAI advancements and maintaining

Qualifications

• Experience building production AI applications using LLMs and agentic workflows.
• Design and implement scalable backend services and APIs.
• Develop RAG pipelines using vector databases and embeddings.

Responsibilities

• Build production-ready AI applications using LLMs and agentic frameworks
• Design and implement scalable backend services and APIs
• Develop RAG pipelines using vector databases and embeddings
• Integrate AI models with enterprise systems and third-party APIs
• Optimize AI workflows for latency, cost, and reliability
• Evaluate and improve LLM performance through prompt engineering and testing
• Collaborate with product and design teams to deliver AI features
• Deploy, monitor, and maintain AI services in production
• Write clean, maintainable, and well-tested code
• Stay updated with the latest advancements in GenAI and agentic AI

Skills

LLMs

Agentic workflows

Backend services

APIs

Prompt engineering

Collaboration

Tools

Vector databases

Embeddings

LLM frameworks

Job description

CodeRound is seeking an AI Engineer in the Philippines to build production-grade AI applications using LLMs and agentic workflows. You will collaborate with product and engineering teams to develop scalable AI solutions, integrate models into real-world products, and optimize performance for enterprise use cases.

You will design backend services, deploy AI features, and continuously improve models through prompt engineering and testing, while staying ahead of GenAI advancements and maintaining