Senior AI Architect & Production LLM Engineer

UNAVAILABLE; McLean (VA); On-site; USD 140,000 - 210,000; Full time

Job summary

UNAVAILABLE is seeking a highly skilled AI Developer to design, build, and optimize advanced AI solutions in predictive, generative, and autonomous domains. You will work end-to-end from data ingestion to deployment, collaborating with product teams and mission stakeholders in a highly technical environment.

You will mentor engineers, implement secure-by-design practices, and stay current with foundation models, agent frameworks, and evaluation tools to continuously improve delivery quality.

Qualifications

• Bachelor's degree and 5 years of relevant experience; OR Master’s degree and 3 years; OR No degree and 9 years of relevant experience.
• Proficiency in Python; comfortable with the AI/ML tooling ecosystem.
• Strong prompt engineering skills and system prompts, few-shot design, and iterative refinement.
• Experience containerizing and deploying apps with Docker.

Responsibilities

• Develop end-to-end AI solutions including LLM-powered applications, predictive ML models, multi-agent workflows, RAG pipelines, and microservices.
• Implement reusable AI components, libraries, and APIs to accelerate delivery across programs.
• Integrate AI models with enterprise systems, APIs, data platforms, vector stores, and cloud-native services.
• Design and implement advanced prompt strategies, context management, retrieval systems, and LLM orchestration logic.
• Build scalable inference services, optimize model performance, and collaborate with LLMOps for deployment and monitoring.
• Mentor junior developers, conduct code reviews, and support engineering excellence.

Skills

Python

LLM orchestration

RAG architectures

Docker

Git

REST APIs

Prompt engineering

AWS

Vector databases

Education

Bachelor's degree

Master's degree

No degree with 9 years experience

Tools

LangChain

LlamaIndex

LangGraph

CrewAI

Job description

UNAVAILABLE is seeking a highly skilled AI Developer to design, build, and optimize advanced AI solutions in predictive, generative, and autonomous domains. You will work end-to-end from data ingestion to deployment, collaborating with product teams and mission stakeholders in a highly technical environment.

You will mentor engineers, implement secure-by-design practices, and stay current with foundation models, agent frameworks, and evaluation tools to continuously improve delivery quality.