AI Engineer, Internship – Intelligent Question Bank Platform

This is a fully remote position, open to applicants in New Jersey.

📋 Description

• You will design and implement the foundational AI pipeline that drives Accel's test creation system.

• Collaborate closely with the founder to conceptualize and develop an AI-driven content generation system from the ground up.

• You will play a significant role in the product's lifecycle, from how the system processes and comprehends source material to how it generates and validates outputs, as well as how instructors engage with and assess the generated content.

• On the engineering front, you will build and refine LLM-driven pipelines, apply retrieval and embedding methodologies to anchor outputs in authentic source material, and create backend services and APIs that integrate all components.

• In addition to coding, you will be required to focus on output quality, establish evaluation procedures, identify failure modes, and enhance the system based on genuine instructor feedback.

• You will investigate emerging tools and techniques as the AI landscape evolves, incorporating relevant innovations directly into the product.

• This position is a generalist role within an early-stage product environment where you will take on various responsibilities, navigate uncertainty, and provide direct input on development processes.

⛳️ Requirements

• Solid foundation in software engineering principles: data structures, APIs, and system design.

• Proficiency in Python, the primary language used for AI/ML pipeline development.

• Experience with REST APIs and familiarity with at least one database, preferably PostgreSQL.

• Ability to work autonomously, pose insightful questions, and iterate quickly.

• Strong debugging skills and problem-solving abilities.

• Proven side projects or deployed code (GitHub portfolio is mandatory).

• Genuine interest in AI technologies and educational solutions.

• Direct experience with LLM APIs such as OpenAI, Anthropic Claude, or Google Gemini.

• Practical experience with RAG systems, including embedding models and vector databases (Pinecone, Weaviate, pgvector, Chroma).

• Familiarity with prompt engineering strategies, including few-shot prompting and structured JSON outputs.

• Experience with NLP pipelines, covering text chunking, tokenization, and semantic search.

• Basic understanding of LaTeX syntax and math rendering libraries like MathJax or KaTeX.

• Experience with image generation APIs or programmatic SVG generation.

• Familiarity with AI evaluation frameworks or automated testing harnesses for LLM outputs.

• Experience with cloud platforms such as AWS, GCP, or Vercel for deployment.

• Familiarity with job queue systems like Celery, Bull, or similar.

• Exposure to educational content standards or psychometrics is considered a plus.

🏝️ Benefits

• All your information will be kept confidential according to EEO guidelines.