Machine Learning Specialist {LLM}  

• Execute performance tuning activities for model serving infrastructure to maintain optimal latency and throughput.
• Conduct post-deployment validation checks to ensure model prediction stability, API responsiveness, and overall service quality.
• Support the enhancement of operational pipelines, including CI/CD workflows, configuration templates, and automated monitoring scripts.
• Participate in service reliability reviews to improve platform uptime, incident response processes, and operational readiness.
• Coordinate closely with DevOps and Platform Engineering to address infrastructure-level concerns related to model hosting and deployment.
• Assist in the rollout of platform-level improvements, including model registry enhancements, container optimization, and new monitoring tools.

Key Requirements: (Must have)

-Machine Learning Operations (MLOPS)
-With Cloud background- AWS, GCP, Azure, Alibaba etc)
-Understanding SQL (Data Pipelines)/ Data Engineering
-Containerization (Docker and Kubernetes)

Other Qualifications:

-Minimum of 2+ years hands-on experience in a production environment covering MLOps, Data Engineering, or Software Engineering.

-Demonstrated ability to meet and exceed strict Service Level Agreements (SLAs), especially those related to system uptime, stability, incident response, and resolution.

-Experience supporting cloud-hosted ML systems in distributed, high-availability environments.

Knowledge:

-Strong understanding of model deployment workflows, including model versioning, serving, rollout strategies, and post-deployment validation.

-Knowledge of cloud platforms (e.g., AWS Cloud) and their native ML services used for hosting, monitoring, and managing model endpoints.

-Familiarity with containerization (Docker) and orchestration (Kubernetes) for scalable ML serving infrastructure.

-Understanding of performance monitoring concepts, including latency tracking, model health indicators, and drift signals.

-Knowledge of CI/CD processes, configuration templates, and automated operational workflows specific to ML systems.

Skills:

-Proven expertise in MLOps, specifically managing model deployment, proactive monitoring, incident resolution, and performance tuning.

-Ability to write and maintain automation scripts, validation utilities, and operational workflows to support ML pipelines.

-Ability to collaborate effectively with DevOps, Data Science, and Platform Engineering teams to improve model reliability and system stability.

-Skilled in applying structured software development methodologies (e.g., Agile/Scrum) to support platform enhancements and iterative delivery.

-Strong analytical, troubleshooting, and root-cause diagnosis skills in production environments.