TS/SCI AI Engineer: LLM & RAG Systems for National Missions

accenturefederalservices; Tampa (FL); On-site; USD 101,000 - 135,000; Full time

Job summary

Accenture Federal Services is seeking an AI Engineer with strong experience in Large Language Models and Retrieval‑Augmented Generation to design, build, and optimize intelligent systems for mission-focused challenges.

The role blends GenAI engineering with traditional CS and ML, supporting rapid prototyping and production-grade delivery, across cloud platforms and containerized workloads, with an active TS/SCI clearance required.

Qualifications

• Hands-on experience with LLMs, prompt engineering, embeddings, vector databases, and RAG frameworks.

Responsibilities

• Design, develop, and maintain RAG pipelines, including document ingestion, embedding generation, vector storage, retrieval logic, and LLM orchestration.
• Build and optimize LLM-powered applications for classification, summarization, Q&A, knowledge retrieval, and workflow automation.
• Apply core software engineering and ML fundamentals to ensure performance, reliability, and security (e.g., data structures, algorithms, model evaluation, MLOps, API development).
• Implement and tune traditional ML models when required (e.g., regression, clustering, feature engineering, classical NLP).
• Integrate cloud-native services (Azure/AWS), data pipelines, and containerized workloads (Docker). Collaborate closely with cross-functional teams-including data engineers, architects, and mission SMEs-to translate requirements into scalable solutions.

Skills

LLMs experience

Prompt engineering

Embeddings

Vector databases

RAG frameworks

Python programming

APIs development

Distributed systems

Tools

Python

Java

C++

PyTorch

TensorFlow

HuggingFace

Docker

Job description

Accenture Federal Services is seeking an AI Engineer with strong experience in Large Language Models and Retrieval‑Augmented Generation to design, build, and optimize intelligent systems for mission-focused challenges.

The role blends GenAI engineering with traditional CS and ML, supporting rapid prototyping and production-grade delivery, across cloud platforms and containerized workloads, with an active TS/SCI clearance required.