AI Full Stack Developer

We are seeking an AI Full Stack Developer to design, build, and deploy end-to-end web applications leveraging Artificial Intelligence (AI) and Large Language Models (LLMs) within a secure Department of War (DoW) environment. This role combines full-stack development (frontend UI, backend APIs, and databases) with modern AI pipeline integration. Position is on-site in Dayton, OH and requires U.S. citizenship.

Responsibilities

• Design, build, and deploy end-to-end web applications integrating AI and LLMs.
• Develop backend logic and APIs using Python frameworks (e.g., FastAPI, Flask).
• Create clean, intuitive user interfaces using modern frameworks (e.g., React, Vue) or AI-focused UI libraries (e.g., Streamlit).
• Manage relational databases (e.g., PostgreSQL) and vector databases (e.g., pgvector, Milvus, Chroma) for application data and AI-searchable embeddings.
• Implement Retrieval-Augmented Generation (RAG) workflows to enable secure AI reference and search of internal documents.
• Containerize applications using Docker/Podman and utilize Git for version control and stable deployment.
• Deploy containerized applications in restricted, disconnected, or IL5+ environments without relying on external cloud connections.
• Utilize open-source AI tools (e.g., Hugging Face) to evaluate, download, and implement open-weight models (e.g., Llama 3, Mistral) locally.
• Optimize AI models for local compute using runtime tools (e.g., vLLM, llama.cpp) and quantization techniques (e.g., GGUF).
• Develop complex AI agent workflows using frameworks like LangChain or LlamaIndex.
• Implement AI safety measures, including guardrails to prevent off-topic outputs and mitigate hallucinations.

Requirements

• U.S. citizenship.
• Must be located in or willing to relocate to the Dayton, OH area.
• Advanced proficiency in Python and API frameworks (e.g., FastAPI, Flask).
• Experience with frontend development using modern frameworks (e.g., React, Vue) or AI-focused UI libraries (e.g., Streamlit).
• Strong experience with relational databases (e.g., PostgreSQL) and vector databases (e.g., pgvector, Milvus, Chroma).
• Hands-on experience designing and implementing Retrieval-Augmented Generation (RAG) workflows.
• Experience with containerization (Docker/Podman) and version control (Git).

Qualifications

• Understanding of secure, air-gapped deployment in restricted environments (e.g., IL5+).
• Experience with the Hugging Face library/hub for open-weight models (e.g., Llama 3, Mistral).
• Familiarity with model runtime tools (e.g., vLLM, llama.cpp) and quantization techniques (e.g., GGUF).
• Knowledge of AI orchestration frameworks (e.g., LangChain, LlamaIndex).
• Ability to implement AI safety and evaluation measures to ensure secure, accurate outputs.

Benefits

• Flexible time off and robust learning resources.
• Comprehensive benefits package including healthcare, wellness, financial, retirement, and family support.
• Continuing education and professional development opportunities.
• Autonomy to balance work and personal life.

Pay

The proposed salary range for this position is $63,300–$129,700. Final salary will be influenced by factors such as geographic location, relevant prior work experience, specific skills and competencies, education, and certifications.

Schedule

• Full-time position.
• Up to 10% local travel may be required.