Senior AI Engineer – RAG/LLM, DoD Security Cleared

Dark Wolf Solutions, LLC; Herndon, Chantilly (VA, VA); Vor Ort; USD 120.000 - 160.000; Vollzeit

Zusammenfassung

Dark Wolf Solutions, LLC seeks a Senior AI Engineer to architect and deploy secure AI-driven solutions for federal and defense enterprises. You will design automated data ingestion pipelines, RAG architectures, and predictive analytics tools to address HR analytics, workflow automation, and scientific literature indexing.

The role requires building NLP pipelines, enforcing DoD security standards, and delivering explainable AI with auditable outputs.

Qualifikationen

• Bachelor’s or Master’s degree in Computer Science, Data Science, AI, ML, or related field.
• 5+ years building production-grade AI/ML systems (3+ with Master/PhD).
• Hands-on experience fine-tuning and deploying LLMs, embeddings, vector databases.

Aufgaben

• Architect Retrieval-Augmented Generation (RAG) systems and LLM agents for enterprise data.
• Build semantic search engines integrating databases, data lakes, literature APIs.
• Implement NLP translation, document classification, and multi-document summarization.
• Develop NLP-driven tasking models for natural language queries with audit trails.
• Design ML algorithms for anomaly detection, predictive modeling, and risk forecasting.
• Collaborate on dashboards with NL querying and drill-down analytics for leaders.

Kenntnisse

Python

PyTorch

TensorFlow

NLP & LLMs

LangChain

FastAPI

Data Pipelines

Ausbildung

Bachelor’s or Master’s in CS/DS/AI

Tools

Pinecone

Milvus

Qdrant

FAISS

Docker

Kubernetes

Jobbeschreibung

Dark Wolf Solutions, LLC seeks a Senior AI Engineer to architect and deploy secure AI-driven solutions for federal and defense enterprises. You will design automated data ingestion pipelines, RAG architectures, and predictive analytics tools to address HR analytics, workflow automation, and scientific literature indexing.

The role requires building NLP pipelines, enforcing DoD security standards, and delivering explainable AI with auditable outputs.