Senior DevOps / MLOps Engineer (AI Platform)

Job Description: DevOps / MLOps Engineer

Title: Senior DevOps / MLOps Engineer (AI Platform)
Department: AI/ML Platform
Reports to: Head of AI/ML
Experience: 4–5 years (hands-on, production)

Role Summary (Read Carefully)

We are building an AI Agent Marketplace with strict requirements around reliability, cost control, observability, and security.
This role owns infrastructure, CI/CD, model deployment pipelines, and runtime stability.

This is not a research role.
This is not a notebook role.
This is production engineering.

If you haven’t supported live systems under load, you are not a fit.

Core Responsibilities (Non-Negotiable)

Platform & Infrastructure

• Design and maintain cloud infrastructure (AWS/GCP/Azure)
• Own Kubernetes or container-based deployment
• Enforce environment separation (dev / staging / prod)
• Manage secrets, credentials, and access policies

MLOps & AI Runtime Support

• Build CI/CD pipelines for:
• Agent definitions
• Model updates
• Prompt & config versioning
• Implement rollback strategies for agents and models
• Enforce resource limits (CPU, memory, tokens, cost)
• Monitor inference latency and failure rates

Observability & Cost Control

• Implement centralized logging (ELK / OpenTelemetry / Prometheus)
• Track:
• Per-agent usage
• Token consumption
• Cost per request
• Build alerts for anomalies and abuse

Security & Reliability

• Secure APIs and runtime execution
• Protect against cost-drain and prompt abuse
• Enforce audit logs and traceability
• Participate in incident response

Required Skills (Must Have)

• Linux (deep knowledge, not basics)
• Docker + Kubernetes
• CI/CD (GitHub Actions, GitLab CI, Jenkins, etc.)
• Cloud infrastructure (IaC preferred: Terraform)
• Monitoring & logging stacks
• Experience deploying ML systems in production

Strongly Preferred (High Signal)

• Experience with LLM deployments
• Token usage monitoring
• Cost optimization for inference workloads
• Multi-tenant system experience
• Security-first mindset

What We Offer

• Competitive salary and equity package.
• Flexible remote/hybrid work options.
• Professional development stipend for courses and conferences.
• Collaborative, fast‑paced environment driving digital commerce innovation.

Job Type: Full-time

Pay: Rs100,000.00 - Rs300,000.00 per month

Experience:

• • CI/CD (GitHub Actions, GitLab CI, Jenkins, etc.): 4 years (Preferred)
• hands-on, production: 4 years (Required)

Work Location: In person