MLOps & AI Infrastructure Engineer – Scalable LLM Deployment (Telecom)

About Us :

Mobileum is a leading provider of Telecom analytics solutions for roaming, core network, security, risk management, domestic and international connectivity testing, and customer intelligence. More than 1,000 customers rely on its Active Intelligence platform, which provides advanced analytics solutions, allowing customers to connect deep network and operational intelligence with real-time actions that increase revenue, improve customer experience, and reduce costs. Know our story : https : / / www.mobileum.com /

Headquartered in Silicon Valley, Mobileum has global offices in Australia, Dubai, Germany, Greece, India, Portugal, Singapore and UK with global HC of over 1800+.

Join Mobileum Team At Mobileum we recognize that our team is the main reason for our success. What does work with us mean? Opportunities!

Role : MLOps & AI Infrastructure Engineer – Scalable LLM Deployment (Telecom)

About the Job :

We are hiring a MLOps & AI Infrastructure Engineer to design and operationalize the AI infrastructure for deploying and scaling LLM-based solutions in our telecom ecosystem. This role focuses on building robust, cost-efficient, and scalable MLOps pipelines, ensuring smooth end-to-end deployment from model training to production inference.

Roles & Responsibility : -

Architect and manage CI / CD pipelines for model training, fine-tuning, deployment, and monitoring.

Set up and optimize GPU / accelerator infrastructure for training and inference workloads, balancing cost-performance trade-offs.

Design and maintain LLM inference services, supporting both batch and low-latency real-time deployments using industry-standard serving tools.

Develop model performance monitoring, logging, and drift detection pipelines with observability frameworks (Prometheus, Grafana, ML flow).

Integrate vector databases and ensure efficient retrieval performance.

Implement A / B testing, canary rollouts, and model rollback mechanisms.

Optimize deployments across cloud environments (AWS, GCP, Azure) and on-premise data centres where applicable.

Desired Profile : -

Experience with low-latency inference optimization

Knowledge of streaming data integrations (Kafka, Spark Streaming) commonly used in telecom.

Prior exposure to telecom operational systems or legacy platform integration.

Familiarity with cost-optimization techniques for AI workloads in high-throughput environments.

Technical skills :

Proven track record of managing enterprise-scale AI systems with a focus on reliability, scalability, and cost-efficiency.

Proficiency in ML infrastructure tooling (Docker, Kubernetes, MLflow, Airflow).

Experience with model serving tools

Deep familiarity with GPU-based workloads, distributed training, and model inference optimization.

Knowledge of cloud platform services (AWS Sagemaker, GCP Vertex AI, Azure ML) including deployment and scaling practices.

Exposure to monitoring, observability frameworks, and incident management for AI workloads

Work Experience :

8+ years of industry experience in MLOps, AI infrastructure, or DevOps for AI systems, with 2+ years in deploying or managing LLM / GenAI pipelines.

Educational Qualification :

Master’s or Ph.D. in Computer Science, Data Engineering, Machine Learning, or a closely related field.

Ph.D. preferred for research-level AI infrastructure optimization.

Location : Bangalore