AI Architect & RAG Data Science Engineer

MTSI is looking for a “Big Data” Scientist and AI Architect to deliver key technical leadership on an ongoing and funded MTSI “STRIKE” IRAD. This IRAD is focused on bringing data taxonomy, data meta-tagging and quality data processes to large dis-organized test data sets and tailoring AI Agents to rapidly locate key data packages needed for model development. More details on the IRAD will be provided to qualified candidates in the interview.

MTSI’s core business concept is to take on and solve our countries most challenging defense requirements. Managing data and optimizing AI to maximize operational capability falls into this problem set. This position will provide ley data expertise across our broad DoW customer base as they address these key challenges.

• Serves as an AI Architect and RAG Data Science Engineer supporting the design, delivery, and continuous improvement of a secure Retrieval-Augmented Generation (RAG) capability. The position requires the individual to design secure, full-stack AI/ML architectures spanning data ingestion, APIs, model services, retrieval, applications, and deployment infrastructure.
• The role translates mission needs into governed data products and full-stack AI services that convert distributed technical, engineering, test, and telemetry information into traceable, role-appropriate answers and analytics. Working with technical and program leadership, the incumbent contributes hands-on expertise across AI/ML, software, cloud, cyber, data engineering, systems engineering, and test.

• Mission and architecture delivery:
  Translate operational, test, and sustainment needs into RAG solution designs, delivery increments, acceptance criteria, and measurable decision-support outcomes under established program priorities.
• Secure RAG and agent implementation:
  Design and implement capabilities spanning source onboarding, document parsing and normalization, metadata and taxonomy management, hybrid retrieval, reranking, LLM inference, citations, guardrails, and agentic workflows using controlled tool use and handoffs; apply llama.cpp or comparable local inference runtimes where permitted.
• Search and retrieval engineering:
  Apply search methods including BM25, TF-IDF, embeddings, hybrid retrieval, metadata filtering, and reranking to improve recall, precision, traceability, and user trust in technical knowledge retrieval.
• Data science and assurance:
  Develop data-quality, retrieval-relevance, groundedness, faithfulness, latency, usefulness, and safety evaluations; maintain curated test sets, analytic baselines, experiments, and performance dashboards to support evidence-based releases.
• Full-stack delivery:
  Contribute to secure user experiences, RESTful APIs, application services, workflow orchestration, data stores, vector databases, integration patterns, and observability needed to operate an AI product at enterprise scale.
• Data and telemetry integration:
  Partner with engineering, test, and data owners to integrate structured and unstructured technical data, test artifacts, logs, sensor or platform telemetry, and operational knowledge while preserving provenance and access controls.
• Dev Sec Ops  and MLOps:
  Apply Git-based development, automated testing, CI/CD, containerization, vulnerability management, model and data versioning, monitoring, auditability, and repeatable deployment across approved environments.
• Collaboration and complex problem resolution:
  Help decompose ambiguous technical problems involving fragmented data, conflicting sources,…