Cactus Communications - MLOps Lead

Overview :

CACTUS is a remote-first organization and we embrace an accelerate from anywhere culture. You may be required to travel to our Mumbai office based on business requirements or for company/team events.

Job Description :

We are looking for an MLOps Lead to design and manage the high-stakes CI/CD pipelines powering our AI/ML deployments. In this role, you will establish foundational mechanisms for model versioning, monitoring, and automated rollbacks to ensure system stability and traceability. You will lead the definition of infrastructure-as-code templates and standardized containerized workflows, ensuring all deployments strictly adhere to Responsible AI guidelines and bias auditing. If you are a technical leader with a deep background in microservices and a passion for building scalable, reproducible ML infrastructure, this role
offers a strategic opportunity to shape our operational excellence.

Responsibilities :

- Design and manage continuous integration and delivery (CI/CD) pipelines for AI/ML models across multiple environments.

- Establish model versioning, deployment, monitoring, and rollback mechanisms to ensure stability and traceability.

- Automate training, testing, and serving workflows using containerized solutions.

- Define infrastructure-as-code templates for scalable AI deployment on on-prem or cloud environments.

- Collaborate with Data Science and Engineering teams to standardize model input/output formats and performance metrics.

- Implement logging, monitoring, and alerting for deployed models to ensure high availability and accuracy over time.

- Ensure compliance with Responsible AI guidelines for deployment, including bias auditing and explainability tracking.

Requirements :

- B.Tech / M.Tech / M.S. in Computer Science, Data Engineering, AI or related discipline.

- Certification in cloud DevOps or MLOps platforms (AWS DevOps Engineer, Azure DevOps Expert, GCP Professional ML Engineer) is highly desirable.

- Contributions to MLOps or DevOps open source projects is preferred.

- 7 to 10 years in machine learning operations or DevOps engineering.

- Minimum 4 years building CI/CD pipelines for AI/ML model deployment in enterprise ecosystems.

- Proven experience with containerized and microservice architectures.

Technical Competencies :

- Containerization : Docker, Kubernetes, Helm charts, container registries, and microservices
architecture for ML workloads

- CI/CD : Jenkins, GitLab CI, GitHub Actions, Azure DevOps with specialized ML pipeline integration

and automated testing

- Infrastructure-as-Code : Terraform, CloudFormation, Ansible for reproducible ML infrastructure
provisioning and management

- Cloud Platforms : AWS (EKS, Lambda, ECR, S3), Azure (AKS, Container Registry, Blob Storage), GCP
(GKE, Cloud Build, Cloud Storage)

- Model Serving : TorchServe, TensorFlow Serving, Seldon, KServe, REST APIs, and real- time
inference infrastructure.

- Programming Languages : Python for automation, Bash scripting, YAML for configuration
management, basic understanding of Go/Java

- Database & Storage : Feature stores (Feast, Tecton), model registries, data versioning (DVC), and
distributed storage systems

- Workflow Orchestration : Apache Airflow, Prefect, Argo Workflows for complex ML pipeline
scheduling and dependency management.

About Cactus :

Established in 2002, Cactus Communications (cactusglobal.com) is a leading technology company that
specializes in expert services and AI-driven products which improve how research gets funded, published,
communicated, and discovered. Its flagship brand Editage offers a comprehensive suite of researcher
solutions, including expert services and cutting-edge AI products like Mind the Graph, Paperpal, and R
Discovery. With offices in Princeton, London, Singapore, Beijing, Shanghai, Seoul, Tokyo, and Mumbai and
a global workforce of over 3,000 experts, CACTUS is a pioneer in workplace best practices and has been
consistently recognized as a great place to work.