MLOps + DevOps Engineer (On-Prem AI Platform)

MLOps + DevOps Engineer (On-Prem AI Platform)

📌 Job ID: QTSNB08358

💼 Experience:  8+ Years

🏢  Work Mode:  Work From Office (WFO)

📍  Location:  Pune

🔹 Role Overview

We are looking for a  Senior MLOps + DevOps Engineer  to architect, build, operate, and scale enterprise  AI/ML platforms in an on-premises environment .

The ideal candidate will have strong experience across  MLOps, DevOps, ML/LLM deployment, Kubernetes/OpenShift, CI/CD, Linux, GPU infrastructure, monitoring, and production reliability .

This role requires end-to-end ownership of ML systems from  data → training → deployment → monitoring .

🔹 Key Responsibilities

Platform Architecture & Ownership

• Design and own end-to-end ML platform architecture.
• Define scalable, secure and reliable MLOps/DevOps standards.
• Standardize MLOps and DevOps frameworks and processes.

Model Deployment & Serving

• Deploy and manage  ML/LLM models on GPU-based on-prem infrastructure .
• Optimize inference for latency, throughput and batching.
• Implement model versioning, A/B testing and rollback strategies.

CI/CD & Automation

• Design CI/CD pipelines for ML models, APIs and data workflows.
• Automate testing, deployment and release management.
• Establish repeatable ML deployment processes.

Infrastructure & Containerization

• Manage  Linux-based on-prem infrastructure ; RHEL preferred.
• Containerize applications using  Docker .
• Deploy and orchestrate workloads using  Kubernetes / OpenShift .
• Operate effectively in restricted or  air-gapped environments .

Data & System Integration

• Build pipelines integrating structured databases and high-volume logs/streaming data.
• Support both batch and real-time inference architectures.

Monitoring & Reliability

• Implement end-to-end observability across ML models and infrastructure.
• Work with  Prometheus, Grafana and ELK Stack .
• Ensure high availability, SLA adherence and effective incident response.

GenAI & Advanced ML

• Deploy  RAG pipelines and vector databases .
• Manage LLM serving frameworks.
• Work with agent orchestration frameworks.

Leadership & Collaboration

• Mentor engineers on MLOps and DevOps best practices.
• Collaborate with ML, Data Engineering, Infrastructure and Application teams.
• Lead design reviews and production-readiness assessments.

🔴 Required Skills

✅  8+ years  in MLOps / DevOps / Platform Engineering

✅ Strong  Python & Bash scripting

✅ Deep understanding of ML lifecycle and productionization

✅ Production deployment of ML/LLM systems

✅ Linux

✅ Docker

✅ Kubernetes / OpenShift

✅ Jenkins / GitLab CI

✅ SQL & Data Pipelines

✅ Production ML platform scaling experience

⭐ Good to Have

• GPU optimization
• MLflow / Kubeflow
• Terraform / Ansible
• On-premises AI/ML platforms
• Restricted / Air-gapped environments
• RHEL

🎯 Ideal Candidate

We are looking for a  hands-on MLOps/DevOps platform architect  who can operate across both  AI/ML systems and infrastructure , driving automation, scalability, security and production reliability.

Strong experience deploying and scaling  production ML/GenAI workloads on on-prem GPU infrastructure  will be highly valuable.

📩  Interested candidates can share their updated CV and mention:

Job ID: QTSNB08358 – MLOps + DevOps Engineer

📧 [email protected]

• #Hiring #MLOps #DevOps #MLOpsEngineer #DevOpsEngineer #AIEngineer #MLPlatform #GenAI #LLM #Kubernetes #OpenShift #Docker #Python #Linux #CI_CD #Jenkins #GitLab #MLflow #Kubeflow #GPU #RAG #OnPrem #PuneJobs #WorkFromOffice #QloronTechnology