Senior MLOps + DevOps Engineer (On-Prem AI Platform)

Role Overview:

We are looking for a Senior MLOps + DevOps Engineer (8+ years) to architect, build, and scale AI/ML platforms in an on-prem enterprise environment.

This role requires end-to-end ownership of ML systems, infrastructure, CI/CD, and production reliability, enabling scalable deployment of machine learning and GenAI solutions.

Key Responsibilities:

1. Platform Architecture & Ownership

- Design and own end-to-end ML platform architecture (data training deployment monitoring)

- Define and enforce best practices for scalable and secure ML systems

- Standardize MLOps + DevOps frameworks and processes

2. Model Deployment & Serving

- Deploy and manage ML/LLM models on GPU-based on-prem infrastructure

- Optimize inference performance (latency, throughput, batching)

- Implement model versioning, A/B testing, and rollback strategies

3. CI/CD & Automation

- Design and implement CI/CD pipelines for ML models, APIs, and data workflows

- Enable automated testing, deployment, and release management

4. Infrastructure & Containerization

- Manage Linux-based (RHEL preferred) on-prem infrastructure

- Containerize applications using Docker

- Deploy and orchestrate workloads using Kubernetes / OpenShift

- Operate within restricted or air-gapped environments

5. Data & System Integration

- Build pipelines integrating structured databases and high-volume logs/streaming data

- Support batch and real-time inference architectures

6. Monitoring, Observability & Reliability

- Implement end-to-end observability (model + infra)

- Use tools like Prometheus, Grafana, ELK stack

- Ensure high availability, SLA adherence, and incident response

7. GenAI & Advanced ML Systems

- Deploy RAG pipelines and vector databases

- Manage LLM serving frameworks

- Work with agent orchestration frameworks

8. Leadership & Collaboration

- Mentor engineers on MLOps and DevOps best practices

- Collaborate with cross-functional teams

- Drive design reviews and production readiness

Required Skills:

- Strong Python and scripting (Bash)

- Deep understanding of ML lifecycle and productionization

- Experience deploying ML/LLM systems in production

- Linux, Docker, Kubernetes/OpenShift

- CI/CD tools (Jenkins/GitLab CI)

- SQL and data pipeline experience

Good to Have:

- GPU optimization knowledge

- MLflow / Kubeflow

- Terraform / Ansible

- Experience in on-prem or restricted environments

Experience:

- 8+ years in MLOps / DevOps / Platform Engineering

- Proven experience scaling production ML systems

Ideal Candidate:

A hands-on platform architect who can operate across ML systems and infrastructure, driving automation, scalability, and reliability.