Machine Learning Platform Engineer

About the role

As a Machine Learning Platform Engineer at ActAI, you will design, build, and operate the core infrastructure that powers the company’s AI products. You will collaborate with AI researchers, engineers, and product teams to turn cutting‑edge models into reliable, scalable production services.

Key responsibilities

• Build and maintain ML infrastructure for model training, evaluation, deployment, and inference.
• Design high‑throughput, low‑latency serving systems using technologies such as vLLM, SGLang, or TensorRT‑LLM.
• Develop robust data pipelines and workflow orchestration for reproducible ML experiments.
• Implement observability, monitoring, tracing, and alerting for AI/ML workloads.
• Identify bottlenecks across the stack and continuously improve reliability, scalability, latency, and cost efficiency.

Required profile

• Strong software engineering fundamentals with experience building production systems.
• Hands‑on experience building ML platforms, model deployment pipelines, or inference services.
• Deep understanding of distributed systems and system reliability.
• Ability to work in fast‑moving, ambiguous environments and take ownership of end‑to‑end solutions.

Required skills

• Python
• PyTorch or JAX
• LLM serving frameworks (vLLM, SGLang, TensorRT‑LLM)
• Cloud infrastructure and distributed systems
• ML/data pipelines and workflow orchestration tools
• GPU infrastructure and performance tooling
• Vector databases and retrieval infrastructure