AI Data Pipeline Engineer

Kavaliro is seeking an AI Data Pipeline Engineer to design and optimize secure, scalable pipelines that move structured and unstructured data into AI processing services and vector databases. This position requires strong expertise in data engineering, AI integration, and performance optimization to support rapid AI workflows.

Responsibilities:

• Develop pipelines using AWS Glue, Lambda, Kinesis, Kafka, NiFi, or Airflow.
• Integrate pipelines with AI/LLM models via RESTful APIs.
• Ensure data quality, caching, and high-speed processing (50–2000 tokens/sec).
• Work with system administrators to maintain compliance with security requirements.
• Document workflows and support evaluation of AI outputs.

Qualifications:

• 3+ years in data engineering or AI infrastructure.
• Strong skills in AWS services, Kafka/NiFi, JSON, Python, and APIs.
• Experience with low-latency pipeline design and optimization.
• Desired: familiarity with LlamaIndex, Qdrant, and classification-aware data processing.

Clearance Requirement: Must hold an active TS/SCI clearance and the ability to pass a CI Polygraph. Applicant MUST hold a permanent U.S. citizenship for this position in accordance with government contract requirements.

Location Requirement: This role is based in Reston, VA or Bolling AFB, DC, with 50% onsite and 50% telework.