AI Engineering Intern

About the role

We are looking for an AI Engineering Intern to help build production AI features for both client‑facing and internal products. The role spans the full AI stack—from prompt engineering and retrieval‑augmented generation to fine‑tuning, evaluation, and deployment—under real shipping deadlines.

Key responsibilities

• Develop LLM‑powered features using providers such as Anthropic, OpenAI, or open‑source models.
• Design and implement RAG pipelines, including embeddings, vector stores, retrieval logic, and evaluation.
• Prototype agentic workflows and tool‑use systems for client use cases.
• Write evaluation harnesses to measure model quality and detect regressions.
• Integrate AI capabilities into existing applications via clean APIs.
• Document patterns and findings to enable team knowledge sharing.

Required profile

• Undergraduate studying Computer Science, AI/ML, Data Science, or equivalent experience.
• Strong Python programming skills.
• Experience with at least one ML/AI library (e.g., PyTorch, Hugging Face, LangChain, LlamaIndex).
• Hands‑on work with an LLM API or open‑source model.
• Practical understanding of transformers, embeddings, and tokenization.
• Ability to read research papers and translate techniques into production code.
• Availability for a 3–6 month internship.

Required skills

• Python
• PyTorch
• Hugging Face
• LangChain
• LlamaIndex
• Anthropic API
• OpenAI API
• Embeddings
• Vector databases (Pinecone, Weaviate, pgvector, Qdrant)
• Evaluation frameworks (Ragas, Promptfoo, LangSmith)
• FastAPI
• Go
• AWS
• GCP
• Modal
• Replicate

What we offer

• Monthly stipend.
• Mentorship from engineers shipping AI to production.
• Portfolio of real AI features deployed to enterprise users.
• Clear path to a full‑time AI engineering role.