Description

Manage the deployment, operation, and optimization of inference services for Auto Recommend and Enhanced Search solutions.

Responsibilities

• Provide Level 3 support for incident management, including diagnosis, resolution, and stakeholder coordination.
• Execute vulnerability management through risk assessment, CVE scanning, patching, and remediation.
• Integrate and operate monitoring and alerting systems to maintain service health.
• Tune and troubleshoot model performance and manage container image deployment.
• Develop and operate end-to-end deployment processes for models and code.

Required Skills

• 15+ years of enterprise consulting experience focused on data, machine learning, and GenAI solutions.
• Proficiency in designing solutions leveraging GenAI, LLMs, and Foundation Models.
• Deep understanding of transformer models, prompt engineering, and model fine-tuning.
• Hands-on experience with vLLM, OpenShift AI, Prometheus, Grafana, and Aqua.
• Proficiency in Python and SQL.
• Experience with Apache Spark, Apache Hadoop, and Informatica.
• Proven ability to build test procedures for data pipeline quality, reliability, and scalability.
• Experience delivering and scaling complex infrastructural solutions across diverse platforms.
• Ability to work within Agile methodologies in collaborative team environments.

Preferred Skills

• University Degree aligned to Data Engineering and/or Data Science.
• Relevant industry certifications such as Databricks Certified Data Engineer, Microsoft, or NVIDIA certifications.

Key Skills

Education

Any Graduate