Veltris is seeking an experienced Platform Engineer specializing in Generative AI to design, build, and operate scalable AI platforms. The role involves developing robust backend services and implementing DevOps practices to support advanced AI capabilities.
Responsibilities:
- Design, build, and maintain platform infrastructure for Generative AI applications
- Develop scalable backend services using Python or Java
- Build and operate production-grade AI systems, including:* AI Agents* Retrieval-Augmented Generation (RAG)* Knowledge Graph based systems
- Implement end-to-end DevOps practices, owning the lifecycle from development through deployment and monitoring
- Design and manage CI/CD pipelines using tools such as GitHub Actions or Jenkins
- Implement Infrastructure as Code (IaC) using Terraform
- Deploy and manage applications on cloud platforms using both:* Cloud-native services* Containerized, cloud-agnostic environments
- Work closely with data scientists, ML engineers, and platform teams to deliver scalable AI infrastructure
Requirements:
- 8+ years of professional experience in software engineering or platform engineering
- Experience from internships, prototypes, or personal projects will not be considered toward the required years
- Strong understanding of system integration and API design with CRM related toolsets
- Strong development experience in Python or Java
- Hands-on experience building production-grade Generative AI systems
- Experience with AI Agents & Retrieval-Augmented Generation (RAG)
- Experience building Knowledge Graph platforms
- Expertise in Graph databases, Metadata ontology, Graph-based RAG architectures
- Strong experience in DevOps culture and practices
- Hands-on experience with CI/CD pipelines (GitHub Actions or Jenkins) & Infrastructure as Code (Terraform)
- Experience deploying and operating systems in cloud environments: Cloud Native (AWS S3, Lambda, AWS batch, AWS ECS) and Kubernetes-based services
- Experience building AI platforms or ML platforms at scale
- Experience with LLM orchestration frameworks (LangChain, Llama Index, etc.)
- Familiarity with vector databases and embedding systems
- Experience in distributed systems and microservices architecture