Reliance Industries Limited
Website:
ril.com
Job details:
We are looking for a skilled DevOps Engineer to build and manage scalable AI infrastructure and deployment pipelines. The ideal candidate will be responsible for creating a seamless transition from model experimentation to production while managing modern LLMOps practices such as prompt versioning, vector database management, and monitoring AI system performance.
Key Responsibilities:
- Design and maintain CI/CD pipelines using tools like GitHub Actions, GitLab CI, or Azure DevOps for backend services and AI agents
- Build automated pipelines to run performance benchmarks before code merges
- Manage and orchestrate LLM deployments (via APIs or self-hosted open-source models)
- Maintain and scale vector databases for RAG-based systems with optimized indexing
- Implement version control for prompts and model configurations
- Automate infrastructure using Terraform or similar tools
- Manage Docker & Kubernetes (K8s) for scalable microservices deployment
- Set up monitoring systems using Prometheus, Grafana, and ELK stack
- Implement AI observability using tools like LangSmith and Arize Phoenix
- Monitor API usage, token costs, and implement caching strategies
- Ensure secure API key management and network-level security for AI systems
Required Skills:
- Strong hands-on experience with Docker & Kubernetes (K8s)
- Proficiency in Terraform for infrastructure automation
- Experience with Azure DevOps (Repos & CI/CD pipelines)
- Monitoring tools: Prometheus, Grafana, ELK Stack
- AI monitoring tools: LangSmith, Arize Phoenix
- Strong scripting skills in Python & Bash
- Knowledge of ETL processes and streaming systems (Kafka / RabbitMQ)
- Solid understanding of cloud infrastructure (AWS/Azure/GCP)
Click on Apply to know more.