Senior AI/ML Data Engineer – Vector AI & RAG

Apavo Corporation; Springfield (VA); On-site; USD 180,000 - 260,000; Full time

Job summary

Apavo Corporation in Springfield, VA seeks a Senior AI/ML Data Engineer to architect the data ecosystem powering vector search, RAG, LLM applications, and Agentic AI for DoD and Intelligence Community clients. You will lead data platforms across infrastructure, cybersecurity, and software engineering to deliver scalable, secure AI solutions.

You will mentor engineers, oversee observability, and evaluate emerging AI technologies, vector databases, and retrieval frameworks while communicating

Qualifications

• Active, current Top Secret/SCI with Polygraph clearance is mandatory.
• Bachelor’s degree in Computer Science, Engineering, Mathematics, Data Science, or related field.

Responsibilities

• Architect, build, and maintain enterprise-scale data platforms supporting vector databases, semantic search, and RAG.
• Lead architectural decisions for AI data infrastructure balancing performance, security, and cost.
• Collaborate with Data Scientists, ML Engineers, Architects, Cybersecurity, and Software Engineers to translate AI requirements into production capabilities.
• Mentor engineers and promote engineering best practices across the organization.
• Assess emerging AI technologies, vector databases, and retrieval frameworks to improve capabilities.

Skills

Python

SQL

Cloud platforms

Vector databases

Observability

Data engineering

AI architectures

Clear communication

Leadership

Education

Bachelor's degree in CS/Engineering/Data Science

Tools

Azure

AWS

GCP

Job description

Apavo Corporation in Springfield, VA seeks a Senior AI/ML Data Engineer to architect the data ecosystem powering vector search, RAG, LLM applications, and Agentic AI for DoD and Intelligence Community clients. You will lead data platforms across infrastructure, cybersecurity, and software engineering to deliver scalable, secure AI solutions.

You will mentor engineers, oversee observability, and evaluate emerging AI technologies, vector databases, and retrieval frameworks while communicating