Description

You will design and maintain a data platform that powers intelligent agents through high-performance data ingestion, contextual memory, and LLM integration.

Responsibilities

• Design and implement scalable real-time and batch data ingestion pipelines using APIs and complex systems like ServiceNow, Google GA4, Jira, and Zendesk.
• Develop and maintain agent memory architecture, including vector stores, knowledge graphs, and temporal data stores.
• Build and manage APIs, event buses, or pub/sub systems to enable agent-to-agent communication.
• Optimize platform performance through data indexing, latency reduction, and load balancing for multi-agent orchestration.
• Implement security, data governance, and versioning practices within agent workflows.

Required Skills

• 5+ years of experience in data engineering, ML platforms, or backend systems.
• Proficiency in Python and SQL.
• Hands-on experience with Apache Spark, Airflow, and dbt.
• Experience integrating APIs and managing data from ServiceNow, Google GA4, Jira, and Zendesk.
• Knowledge of vector databases and semantic search.
• Experience building event-driven architectures using Kafka or Pub/Sub.
• Understanding of LLM orchestration, prompt engineering, and tool-use paradigms.
• Experience working within cloud platforms such as AWS, GCP, or Azure.
• Strong analytical and problem-solving skills for identifying performance bottlenecks.

Preferred Skills

• Experience with RAG (retrieval-augmented generation), knowledge graphs, or multi-agent systems.
• Familiarity with LangGraph, DSPy, or agent state management tools.
• Exposure to observability tools like DataDog, Prometheus, Grafana, or OpenTelemetry.

Key Skills

Education

Any Graduate