AI Infrastructure Engineer
Virtualyyst
Description
Position: AI Infrastructure Engineer
Experience Required: 4 to 6 years
Employment Type: Full-Time
About The Role
We are seeking a strong AI Engineer with a heavy focus on infrastructure and production-grade AI systems. This role is ideal for someone who enjoys building scalable AI backends, setting up robust data and MLOps pipelines on GCP, and deploying agentic AI applications end-to-end. If you are passionate about AI infrastructure, cloud-native systems, and real-world AI deploymentnot just experimentationthis role is for you.
Key Responsibilities
- Design and build AI infrastructure using Python or Rust with a strong focus on performance and scalability.
- Set up end-to-end data pipelines from APIs to storage layers such as AlloyDB or CloudSQL.
- Design and manage data models to support AI workloads and application requirements.
- Build and maintain GCP-based MLOps pipelines for training, deployment, monitoring, and versioning.
- Develop and deploy AI applications using Vertex AI, including RAG-based and agentic workflows.
- Implement agentic tool usage and orchestration for multi-step AI workflows.
- Build FastAPI-based backend services and token-streaming endpoints for real-time AI responses.
- Ensure reliability, observability, and security of AI systems in production environments.
- Collaborate closely with product, data, and frontend teams to deliver scalable AI solutions.
Skills & Requirements
- Strong programming background in Python or Rust.
- Hands-on experience with GCP, especially Vertex AI and cloud-native services.
- Solid experience in MLOps, including model deployment, monitoring, and pipeline automation.
- Strong understanding of data modeling and backend data pipelines.
- Experience setting up API-driven data ingestion and storage using AlloyDB or CloudSQL.
- Hands-on experience with FastAPI and building production-grade APIs.
- Practical experience with RAG architectures and agentic AI workflows.
- Understanding of token streaming, latency optimization, and scalable AI serving.
Nice To Have
- Experience with containerization and orchestration (Docker, Kubernetes).
- Familiarity with vector databases and embedding pipelines.
- Exposure to LLM observability, evaluation, and cost optimization strategies.
- Prior experience building AI systems at scale in production environments.
(ref:hirist.tech)
Posted 21 Mar 2026 · Listing from OnJob.io. Create a free profile to apply and see your AI match score.
Related Data & AI jobs
Hand-picked roles that match this listing on skills, category and location — each scored to your profile inside OnJob.