AI Engineer – Agentic Data Platform

Key Responsibilities

• Design and architect agentic AI pipelines and multi-agent systems for data ingestion, transformation, processing, and analytics.

• Build and optimize Lakehouse-based solutions on Databricks, including ETL/ELT pipelines, Delta Lake storage, and ML model operationalization.

• Implement and orchestrate AI Agents using tools such as Google Vertex AI Agent Builder, Aera/AREA, or similar agentic platforms.

• Integrate LLMs and foundation models into autonomous workflows for analytics and decisioning.

• Develop, test, and deploy RAG pipelines and LLMOps workflows for domain-specific knowledge and reasoning tasks.

• Implement best practices for prompt engineering, fine-tuning, responsible AI, and guardrails in production.

• Collaborate with Data Engineering, MLOps, and Product teams to ensure scalability, performance, and security of the agentic platform.

• Monitor performance and optimize deployed agents and AI workflows.

Required Skills & Qualifications

• 5–8 years of experience in AI/ML Engineering, Data Engineering, or Applied AI roles.

• Strong expertise in Databricks (PySpark, Delta Lake, MLflow, Unity Catalog).

• Hands-on experience with agentic frameworks and toolkits, such as:

  • Google Vertex AI Agent Builder

  • Aera/AREA Agentic Platform

  • OR open-source frameworks (LangChain, AutoGen, CrewAI, HuggingFace ecosystem)

• Strong Python skills with experience developing scalable AI/ML applications.

• Experience deploying LLMs, RAG workflows, and working with vector databases (Pinecone, Weaviate, Chroma, BigQuery Vector Search).

• Good understanding of MLOps / LLMOps: CI/CD, model versioning, experiment tracking, model monitoring.

• Familiarity with cloud environments (GCP preferred; AWS/Azure a plus).

• Strong system design, problem-solving, and debugging abilities.

Nice-to-Have

• Experience developing autonomous decisioning systems for manufacturing, supply chain, finance, or enterprise automation.

• Exposure to streaming platforms such as Kafka, Kinesis, Pub/Sub.

• Knowledge of graph-based reasoning, enterprise knowledge models, or knowledge graphs.

• Experience integrating with enterprise platforms such as SAP, Salesforce, ServiceNow, etc.

Soft Skills

• Excellent verbal and written communication.

• Strong ownership mindset with the ability to work independently.

• Ability to collaborate effectively with diverse technical and business teams.

Education

• Bachelor’s or Master’s degree in Computer Science, Software Engineering, Data Science, AI/ML, or other relevant fields (or equivalent experience).