MlOps Engineer

Superteams.ai helps businesses build agentic systems, deploy private LLMs, and power next-gen AI workflows. Our company blends AI expertise, cloud infrastructure, and open-source technologies to help clients build, scale, and maintain custom AI solutions across sectors like education, climate, and enterprise SaaS.

Our work spans a wide spectrum of Generative AI applications -  from LLMs and vision models to audio synthesis and predictive analytics. If you’re passionate about infrastructure that supports cutting-edge AI systems, you’ll thrive here.

What You’ll Do

MLOps Engineer

Key Responsibilities

• Set up and manage cloud infrastructure (AWS, GCP, or Azure) for AI and data applications.

• Build and maintain CI/CD pipelines for deploying AI systems and services.

• Containerize applications using Docker and orchestrate using Kubernetes.

• Set up observability and monitoring tools such as ELK, Prometheus, Grafana, Loki, and Graylog.

• Manage logging, alerting, and performance tracking for uptime, latency, and failure detection.

• Automate infrastructure provisioning and updates using IaC tools and scripting.

• Collaborate with AI engineers to enable smooth deployments of LLMs and agentic systems.

• Assist in database performance optimization (SQL, NoSQL and Vector DBs).

Must-Have Skills

• Very strong command of

  Linux/Ubuntu

  systems and shell scripting. You should be able to operate a remote server comfortably.

• Hands-on experience with at least one cloud platform:

  AWS, GCP, or Azure

  . Just being able to see the dashboard on AWS isn’t enough - you should know how to manage instances, track system health, handle firewalls, and audit logs.

• Proven expertise in

  CI/CD pipeline management

  . You should have worked with Jenkins, Ansible or any industrial-grade CI/CD platform.

• Solid understanding of

  Docker

  and

  Kubernetes

  . You should have managed containers, Docker swarms, or handled scalability challenges in production systems.

• Experience with

  monitoring, alerting

  , and

  log centralization tools

  like Elastic-Kibana, Prometheus, Grafana, Graylog or Loki. You should also be aware of Sentry and other monitoring systems.

• Experience managing

  uptime, load balancing

  , and

  failover systems

  . Understanding of snapshotting, firewalls, recovery, failover and zero-downtime is a must.

Nice to Have

• Experience with vLLM for LLM serving and handling batching, queueing, retries and error handling with LLM requests.

• Working knowledge of

  Python

  for scripting and automation. You should be able to understand Python code, debug it to some extent and fix issues that may happen in production.

• Deep experience with

  SQL databases

  (e.g., PostgreSQL, MySQL).

• Interest in or exposure to

  AI infrastructure

  , model serving, and agentic system design.

What You’ll Gain

• Exposure to the latest in Generative AI and agentic systems.
• Hands-on experience with AI devops challenges: model hosting, scaling inference, observability in multimodal systems, and more.
• Opportunity to contribute to open-source AI infrastructure tools.
• A fast-paced, collaborative environment where learning and innovation are at the core.

If you're excited to build scalable infrastructure that enables cutting-edge AI, we’d love to hear from you.