DevOps & AI Infrastructure Engineer

We have completed development of a social media chat application with AI-powered features, and we are now preparing for full-scale production deployment.

We are seeking an experienced DevOps & AI Infrastructure Engineer who can take complete ownership of:

Production deployment

Cloud infrastructure setup

Auto-scaling architecture

GPU/AI model management

Ongoing monitoring & daily operational support

This role requires hands-on execution, guidance, and long-term support to ensure a smooth, stable, and scalable launch.

Scope of Work:

::::

Production Deployment

Deploy backend services, APIs, databases, and AI services to production

Configure secure cloud infrastructure (AWS / GCP / Azure preferred)

Set up CI/CD pipelines for continuous deployment

Ensure zero-downtime deployment strategies

Infrastructure & Auto-Scaling

Design and implement auto-scaling architecture

Configure load balancers

Set up container orchestration (Docker + Kubernetes preferred)

Optimize performance for high concurrent users

Plan infrastructure for scaling from thousands to millions of users

AI Models & GPU Management

Deploy and manage AI models in production

Configure and manage GPU instances

Optimize inference performance and latency

Monitor AI workloads and resource utilization

Coordinate with AI team for updates, fine-tuning, and scaling requirements

Monitoring & Reliability

Implement monitoring systems (Prometheus, Grafana, Datadog, etc.)

Set up alerts and logging systems

Handle incident response and troubleshooting

Daily health checks of production systems

Ensure high availability and uptime (99.9%+ target)

Security & Compliance

Configure secure networking (VPC, firewalls, private subnets)

Manage SSL, encryption, and secrets handling

Implement best practices for infrastructure security

Protect AI models and user data

Ongoing Support & Guidance

Provide daily operational oversight

Proactively detect and fix issues

Guide team in infrastructure decisions

Assist in performance optimization

Help plan future scaling strategies

This is not a one-time deployment — we need someone who will support us during and after launch.

Required Skills

Strong experience with AWS / GCP / Azure

Kubernetes & Docker expertise

Experience deploying AI/ML models in production

GPU infrastructure management (NVIDIA, CUDA environments)

CI/CD pipeline setup

Infrastructure as Code (Terraform preferred)

Experience handling high-traffic applications

Strong monitoring & observability experience

Database scaling (PostgreSQL / MongoDB / Redis)

Preferred Experience

Experience deploying real-time chat applications

Experience with AI inference pipelines

Experience optimizing model latency and GPU cost

Experience with WebSocket-based applications

Knowledge of autoscaling GPU clusters

Engagement Model

Immediate start

Full deployment support required

Daily monitoring & long-term collaboration

Must be available for real-time communication during critical deployment phase

Our Expectations

We need someone who:

Takes ownership

Thinks proactively

Solves problems independently

Guides us technically

Acts like a technical partner, not just a freelancer

Contract duration of 3 to 6 months.

Mandatory skills:

Cloud Infrastructure (AWS / GCP / Azure), Kubernetes (K8s) Orchestration, Docker Containerization, GPU Infrastructure & NVIDIA CUDA Management, AI/ML Model Deployment & Optimization, CI/CD Pipeline Implementation, Infrastructure as Code (Terraform), Auto-Scaling & Load Balancing, Monitoring & Observability (Prometheus, Grafana, ELK), Database Scaling & Performance Optimization (PostgreSQL / MongoDB / Redis)