ML Platform Engineer (AI) – Remote

About the role

As an ML Platform Engineer (AI) you will design, build, and maintain the internal infrastructure that powers AI‑driven applications. You will bridge the gap between machine‑learning research and production, ensuring models are deployed reliably and at scale.

Key responsibilities

• Architect and manage production‑grade AI infrastructure, including model gateways and agent deployment platforms.
• Design automated evaluation pipelines to validate LLM outputs.
• Build and optimize scalable vector stores for retrieval‑augmented generation.
• Deploy and operate high‑performance LLM serving solutions using frameworks such as vLLM and TGI.
• Implement observability and monitoring to track model performance and system health.
• Collaborate with application teams to standardize continuous training, inference, and security workflows.

Required profile

• 4+ years of experience in ML platform engineering, DevOps, or infrastructure engineering.
• Proven track record building internal AI infrastructure, model gateways, and evaluation pipelines.
• Strong expertise with Kubernetes and Docker for container orchestration.
• Hands‑on experience with LLM serving frameworks (vLLM or TGI) and cloud AI services (AWS Bedrock, Azure OpenAI).
• Advanced proficiency in Python and observability tools.
• Fluent English communication skills.

Required skills

• Kubernetes
• Docker
• Python
• vLLM
• TGI
• AWS Bedrock
• Azure OpenAI
• Langfuse or LangSmith

What we offer

• 100% remote work from anywhere.
• Competitive compensation in USD or local currency.
• Provided hardware and software setup for home office.
• Flexible schedule – create your own hours.
• Paid parental leave, vacations, and national holidays.
• Multicultural environment with top‑tier global talent.
• Mentorship, promotion pathways, and continuous skill development.