GenAI ML/LLM Operations Engineer

• Model Deployment and Management: Deploy, monitor, and maintain generative models (including LLMs and image generators) in a production environment, ensuring high availability and optimal performance.
• Model Comparison & Selection: Evaluate and compare various GenAI models based on accuracy, latency, cost, and relevance to specific content generation tasks.
• Model Transformation & Optimization: Apply fine-tuning, quantization, and other optimization techniques to enhance model performance and resource efficiency.
• Designing, implementing, and optimizing generative AI models for various market applications, while evolving the platform with newer GenAI frameworks, agents, models.
• Infrastructure Management: Design and manage the infrastructure supporting GenAI workloads, including compute, networking, and storage, primarily on GCP.
• Performance Monitoring and Optimization: Implement robust monitoring and alerting systems to identify and address performance bottlenecks, latency issues, and other anomalies.
• Cost Management: Optimize resource utilization and implement cost-saving measures to minimize the operational expenses associated with LLM infrastructure.
• Agentic Framework Support: Experience of integration of agentic workflows using frameworks such as LangGraph and Google's Agent2Agent (ADK), MCP, and support their deployment into production environments.
• Collaboration: Work closely with data scientists, ML engineers, and platform teams to ensure seamless end-to-end delivery of GenAI solutions.
• Security and Compliance: Implement security best practices to protect LLM infrastructure and data from unauthorized access and ensure compliance with relevant regulations.
• Troubleshooting and Support: Act as a primary responder for GenAI-related operational issues, providing timely troubleshooting and resolution
• Staying Current: Stay informed on advancements in GenAI and agentic systems, and proactively identify opportunities for innovation and process improvement.
• Direct interactions with Architecture, Application/Platform, and Technical Product teams to guide technology selections.

• Proficient in Google Cloud Platform (GCP) services, particularly Vertex AI, BigQuery, GKE, Cloud Run, and Cloud Functions.
• Experience deploying and optimizing LLMs, image generation models, or other GenAI models in cloud environments..
• Experience with evolving technologies like MCP and A2A - and the ability to apply them in a business and marketing context
• Ability to design and implement scalable AI computing infrastructures and application stacks for efficient ML operations
• Familiarity with emerging agentic architectures, including LangGraph, Agent2Agent (ADK), or similar frameworks.
• Understanding of the technical aspects of RAG models, how to retrieve relevant information from knowledge bases and integrate it with LLM output, including their training process and how retrieved information is used to enhance generation
• Working knowledge of NLP, computer vision, and multimodal AI model operations.. Model Transformation Techniques: Experience with techniques like quantization, pruning, and knowledge distillation for optimizing LLMs.
• Familiarity with ML frameworks such as Transformers, PyTorch, or TensorFlow
• Containerization and Orchestration: Proficiency in containerization technologies (e.g., Docker, Kubernetes) and orchestration tools.
• Hands-on experience with monitoring and logging solutions, including open-source tools (e.g., Prometheus, Grafana, ELK stack) and cloud-native platforms such as Google Cloud Logging and Cloud Monitoring.
• Automation: Strong scripting and automation skills (e.g., Python, Bash).
• Knowledge of security best practices in cloud and AI infrastructure.
• Excellent communication skills, capable of articulating technical visions and strategies to a diverse audience, fostering cross-functional collaboration and consensus.
• Eager to embrace new technologies, methodologies, and industry developments, with a commitment to lifelong learning and professional growth.
• Evaluation of ML and LLM models, required

MyCarriera