AI Platform Engineering and MLOps/LLMOps Resident Strong exp in NIM Triton NeMo RAPIDS and GPU placement and CI/CD or GitOps and environment promotion

About Avensys Consulting

Avensys Consulting is a global IT professional services company headquartered in Singapore. The company provides enterprise solution consulting, business intelligence, business process automation, and managed services. With over a decade of operation, Avensys Consulting serves clients across banking and financial services, insurance, information technology, healthcare, retail, and supply chain sectors.

The Role: AI Platform Engineering and MLOps/LLMOps Resident

Avensys Consulting is seeking an AI Platform Engineering and MLOps/LLMOps Resident to join their team in Riyadh. This full-time position requires 5-10 years of experience and focuses on developing and implementing AI platform solutions. The role involves working with technologies such as NIM, Triton, NeMo, RAPIDS, GPU placement, CI/CD, and GitOps to establish robust AI/ML environments.

Key Responsibilities

• Define reusable NIM and Triton deployment patterns for H200 and L40S pools.
• Establish templates for model packaging, endpoint configuration, resource requests, GPU placement, health checks, logging, metrics, security controls, and rollback.
• Support controlled model customization and fine-tuning workflows using NeMo on dedicated H200 capacity.
• Utilize RAPIDS for GPU-accelerated data preparation, embeddings, document processing, and related pipeline stages.
• Define the governed model lifecycle, including experimentation, registration, evaluation, approval, deployment, monitoring, rollback, and retirement.
• Establish evaluation gates for quality, grounded-answer rate, latency, concurrency, availability, safety, and operational readiness.
• Define CI/CD or GitOps patterns for repeatable promotion between development, validation, and production environments, adhering to MOJ standards.
• Create RAG and document-intelligence onboarding patterns covering data approval, ingestion, chunking, embeddings, vector indexes, access control, and rollback.

Required Experience and Skills

• Strong experience in AI Platform Engineering and MLOps/LLMOps.
• Proficiency with NIM, Triton, NeMo, and RAPIDS.
• Experience with GPU placement strategies.
• Demonstrated knowledge of CI/CD or GitOps practices.
• Familiarity with environment promotion processes.
• 5-10 years of relevant professional experience.

Compensation and Benefits

The successful candidate will receive a competitive base salary and attractive company benefits. This role offers opportunities for career progression within a collaborative work environment.