Senior ERP Specialist

Job Summary

ML Ops(Years Experience)Role Summary We are seeking a highly experienced Senior Agentic AI Developer to join the Availability & Reliability Team (ART) under the EPE organization. This role focuses on the development and productionization of autonomous, task-oriented AI agents designed to optimize internal engineering workflows, automate complex problem-solving, and enhance platform efficiency. The ideal candidate will leverage the latest breakthroughs in reasoning and multimodal processing provided by the Gemini 3 family to build scalable, agentic solutions within the Google ecosystem.Required Skills1. Minimum 5+ years of experience in Machine Learning Engineering or Software Engineering with a strong focus on AI operations and MLOps.2. Hands-on experience with MLOps frameworks, including building automated model refresh cycles, metrics collection pipelines, and monitoring systems.3. Proficiency in Large Language Models (LLMs) and Prompt Engineering, with a specific focus on the Gemini model family (2.5, 3.0).4. Advanced programming skills in Python or Java, with experience building data automation pipelines and integrating with Vertex AI or similar ML platform APIs.5. Expertise in advanced NLP benchmarking tools such as BLEURT, BERTScore, and Mean Absolute Error (MAE) for temporal precision.6. Platform & Pipeline Engineering: Designing and configuring MLOps stacks (e.g., Kubernetes, feature stores), packaging models, and automating CI/CD pipelines for repeatable rollouts.7. Reliability & Governance: Monitoring model accuracy and data drift, optimizing inference performance and costs, and setting up access controls and compliance tools.8 Operational Consulting: Assessing workflows to define maturity paths, running ML operations long-term via embedded teams, and training internal data scientists on self-service tools.Preferred Skills1. Exposure to Audio (e.g. sampling rates, audio formats, stateful media) and related ML fundamentals and frameworks (Affective Dialogue, Live API etc.)2. Domain expertise in Speech-to-Text (STT), Speech-to-Speech and NLP.3. Familiarity with internationalization (i18n) requirements for APAC and diverse global locales.4. Knowledge of infrastructure reliability strategies, such as handling rate limits (429 errors) and implementing multi-tier durability (Online to Batch fallback).5. Hands-on experience with LLM orchestration frameworks (e.g., Lang Chain, Lang Graph) and building state-of-the-art Retrieval-Augmented Generation (RAG) pipelines.Key Responsibilities Need to deliver Following:Infrastructure Artifacts: ML platform architecture blueprints, scalable model-serving layers, and automated workflow orchestrations for data ingestion and training.Automated model refresh cycles and metrics collection pipelines.Lifecycle Trackers: Versioned catalogs for models and data, experiment tracking for reproducibility, and automated CI/CD builds with staging environments.Monitoring & Enablement Tools: Prediction latency dashboards, incident playbooks, regulatory compliance packages, and internal self-service UIs Agentic Workflow Design: Architect and orchestrate autonomous agents capable of planning, executing, and v

Key Responsibilities

1. To manages the overall ERP environment, including multiple modules and integrations.

2. To monitor occurrences of new software releases, support packs and kernel upgrades and how these affect the application and users.

3. Proactively identifies opportunities for improvement and optimization across the ERP system, aligning with business goals.

4. To perform troubleshooting for complex technical issues at the ERP and database level.

5. To stay updated on emerging ERP technology trends and transfer knowledge to the team members.

Skill Requirements

null

Other Requirements

null