Back to jobs

Jr. Artificial Intelligence Engineer

Solarion AI
Washington DC-Baltimore Area
Full-time
AI tools:
LLaMA
OpenAI API
Applications go directly to the hiring team

Join Solarion AI as a Junior Artificial Intelligence Engineer to design cutting-edge intelligent document systems. You will work closely with a collaborative team on innovative AI workflows that have a substantial impact on enterprise efficiency and decision-making.

Full-time
Entry Level

Skills & Expertise

LLM integration
RAG pipelines
vector search
prompt engineering
AI APIs
backend integration
performance optimization
document systems

Key Responsibilities

Develop AI workflows using LLMs like LLaMA and OpenAI API.

Build and optimize retrieval-augmented generation pipelines.

Collaborate with teams to integrate AI into enterprise workflows.

Full Description

Intern AI Engineer – Solarion AI (AURA Platform)

AI Engineers at Solarion AI design and build production-grade intelligent document systems that transform enterprise content into structured, usable intelligence. The role focuses on developing and operationalizing LLM-powered workflows using models such as LLaMA, Amazon Bedrock, and OpenAI API.

They work on the end-to-end AI lifecycle—from prompt design and model integration to deployment and optimization—building scalable systems that support document understanding, semantic search, and context-aware reasoning across enterprise datasets.

The role involves developing retrieval-augmented generation (RAG) pipelines, integrating vector search, and enabling grounded responses over complex document repositories. Engineers also contribute to multi-model orchestration, selecting and optimizing models across providers based on cost, latency, and performance requirements.

Working closely with product and engineering teams, they help embed AI into workflows such as clause extraction, summarization, and decision support, ensuring outputs are reliable, explainable, and aligned with enterprise standards.

Note on Hiring

We are actively seeking college interns and fresh graduates interested in building real-world AI systems. This role provides hands-on exposure to LLMs, RAG architectures, and production AI workflows in an enterprise environment.

Candidates should have a strong foundation in computer science fundamentals, along with curiosity and willingness to learn modern AI systems and tools.

Core Focus Areas

* LLM integration (LLaMA, OpenAI, Bedrock)

* RAG pipelines & vector search

* Prompt engineering and evaluation

* AI APIs and backend integration

* Performance optimization (latency, cost, accuracy)

Applications go to the hiring team directly