Position : Senior Red Hat AI Stack Developer / Architect

Experience : 6 to 10 Years

Location : Infobell Office, Bangalore

Work Mode : Work from Office

Role Summary :

We are looking for an experienced Senior Red Hat AI Stack Developer / Architect to design, implement, and manage enterprise-scale AI, ML, and Generative AI solutions using Red Hat technologies, including Red Hat OpenShift AI (RHOAI) and Red Hat AI Enterprise, across hybrid and multi-cloud environments.

The ideal candidate will work closely with platform, application, and data teams to build secure, scalable, and production-ready AI platforms leveraging Kubernetes architecture and modern MLOps / GenAI Ops practices.

Key Responsibilities :

- Design and implement enterprise AI/ML and Generative AI architectures using Red Hat OpenShift AI.

- Build and manage end-to-end AI/ML pipelines covering training, evaluation, deployment, and monitoring.

- Develop scalable LLM inference solutions, including RAG (Retrieval-Augmented Generation) workflows.

- Integrate AI workloads with OpenShift, RHEL, automation, and observability platforms.

- Collaborate across engineering and business teams to productionize AI use cases.

- Implement MLOps / GenAI Ops practices, including CI/CD, monitoring, drift detection, and retraining strategies.

- Create reference architectures, reusable frameworks, and deployment standards.

- Drive AI platform adoption through architecture governance and technical leadership.

Required Skills :

- Strong expertise in Kubernetes and Red Hat OpenShift

- Hands-on experience with OpenShift AI (RHOAI) or equivalent AI platforms

- Experience across the complete AI/ML lifecycle :

1. Model training

2. Fine-tuning

3. Inference

4. Monitoring

- Strong understanding of LLM, RAG, and Generative AI workflows

- Experience with MLOps tools such as Kubeflow, MLflow

- Programming proficiency in Python and/or Go

- Experience with AWS / Azure / GCP

- Knowledge of AI architecture, scalability, and performance optimization

- Experience with GPU optimization and distributed inference

Good to Have :

- Experience with vLLM and LLM inference optimization

- Knowledge of LLM-D architecture and distributed inference models

- Exposure to Red Hat AI Enterprise / RHEL AI

- Experience building Agentic AI workflows

- Familiarity with modern AI frameworks and orchestration tools

Success Metrics :

- Faster enterprise adoption of Red Hat AI platforms

- Standardized and scalable AI solution architecture

- Improved deployment efficiency and platform maturity

- Strong stakeholder collaboration and successful solution delivery