Generative AI Engineer

Beyondsoft; Kuala Lumpur; Presencial; MYR 140.000 - 240.000; Jornada completa

Descripción de la vacante

Beyondsoft is seeking a hands-on AI Engineer to design, develop, and deploy production-grade AI applications focusing on Agentic AI, multi-agent systems, and RAG pipelines. The role combines strong Python and backend development with experience integrating LLMs into enterprise data and deploying scalable AI solutions.

You will work on cloud-based AI solutions, containerized deployments, and production-grade services, ensuring reliability, security, and measurable business impact.

Formación

• Bachelor's degree in CS/Engineering or equivalent.
• 4+ years in software/AI backend roles.
• Strong Python and API development experience.
• Experience building Agentic AI apps and multi-agent workflows.
• Practical RAG solutions with embeddings and vector databases.
• Cloud deployment to AWS, Azure, or GCP.

Responsabilidades

• Design AI agents and multi-agent workflows across platforms.
• Build and optimize RAG pipelines for quality and speed.
• Develop scalable Python backends and APIs.
• Deploy AI apps on cloud platforms and manage security.
• Deploy, monitor, and maintain production systems.
• Evaluate model outputs, latency, and cost metrics.
• Integrate LLMs with enterprise data sources.
• Collaborate with product and engineering teams.

Conocimientos

Agentic AI

Multi-Agent Systems

RAG & LLM Engineering

Python

Backend Development

Cloud Platforms

Docker/Kubernetes

CI/CD

Educación

Bachelor's degree in CS/Engineering/AI

Herramientas

LangGraph

CrewAI

LangChain

Semantic Kernel

PostgreSQL

Redis

Elasticsearch

CosmosDB

CUDA

Descripción del empleo

We are seeking a hands-on AI Engineer to design, develop, and deploy production-grade AI applications, with a focus on Agentic AI, multi-agent systems, Retrieval-Augmented Generation (RAG), and cloud-based AI solutions. The ideal candidate combines strong Python and backend engineering skills with practical experience building AI-powered applications, integrating LLMs with enterprise data, and deploying scalable, secure, and reliable solutions in production environments.

WHAT YOU WILL BE DOING:

• Agentic AI & Multi-Agent Systems: Design and implement AI agents and multi-agent workflows using frameworks such as LangGraph, CrewAI, LangChain, or similar technologies. Develop solutions involving tool calling, task orchestration, workflow automation, and agent collaboration.
• RAG & LLM Engineering: Build and optimize RAG pipelines, including document processing, chunking, embeddings, vector search, hybrid retrieval, reranking, and context management to improve response quality.
• Python & Backend Development: Develop scalable backend services and APIs using Python, FastAPI, or equivalent frameworks. Integrate AI capabilities with databases, enterprise applications, and external systems.
• Cloud AI Solutions: Build and deploy AI applications using cloud platforms such as AWS, Azure, or Google Cloud. Integrate managed AI services and model APIs based on project requirements.
• Production Deployment: Deploy, monitor, and maintain AI applications using Docker, Kubernetes, CI/CD pipelines, and cloud-native services. Ensure reliability, scalability, and maintainability beyond the proof-of-concept stage.
• AI Evaluation & Optimization: Evaluate LLM outputs, retrieval quality, latency, and cost. Implement automated testing, tracing, observability, guardrails, and human-in-the-loop controls.
• Data & Model Integration: Work with LLMs, embedding models, vector databases, and structured and unstructured data sources. Apply prompt engineering, model selection, and fine-tuning techniques where appropriate.
• Security & Reliability: Implement secure API integrations, access controls, data protection, and responsible AI practices.
• Cross-Functional Collaboration: Partner with product, engineering, and business teams to translate requirements into effective AI solutions and measurable business outcomes.

Qualifications

MINIMUM QUALIFICATIONS:

• Bachelor's degree in Computer Science, Software Engineering, AI, or a related field, or equivalent practical experience.
• 4+ years of experience in software engineering, AI/ML engineering, or backend development.
• Strong hands-on Python development experience, including API development with FastAPI or similar frameworks.
• Demonstrated experience building Agentic AI applications, multi-agent workflows, or LLM-powered automation.
• Practical experience developing RAG solutions using embeddings, vector databases, and retrieval techniques.
• Experience integrating LLMs and AI services into backend applications and enterprise systems.
• Experience deploying applications to a cloud environment such as AWS, Azure, or GCP.
• Familiarity with Docker, Kubernetes, CI/CD, application monitoring, and production troubleshooting.
• Strong problem-solving skills and the ability to deliver maintainable, production-ready code.

PREFERRED QUALIFICATIONS:

• Experience with LangGraph, CrewAI, LangChain, Semantic Kernel, or similar agentic frameworks.
• Experience with managed AI services such as AWS Bedrock, Azure OpenAI, Azure AI Foundry, or Google Vertex AI.
• Familiarity with PostgreSQL, Redis, Elasticsearch, Cosmos DB, or other vector and data storage technologies.
• Experience with LLM fine-tuning techniques such as LoRA or QLoRA.
• Knowledge of inference optimization, model quantization, GPU utilization, or CUDA.
• Experience with AI evaluation frameworks, observability, tracing, guardrails, and production performance optimization.
• Familiarity with Go, TypeScript, React, or other technologies used in full-stack application development.