We’re looking for a curious and driven AI / LLM Engineering Intern who wants hands-on experience building real AI systems — not just following tutorials. You’ll work closely with our engineering team to prototype and deploy AI agents, LLM-powered tools, and intelligent automation workflows.

If you enjoy experimenting with prompts, building scrappy prototypes, testing model behavior, or figuring out how to make AI solve actual business problems, this role is for you.

What You’ll Work On

1. Building small AI agents using frameworks like LangChain, LlamaIndex, CrewAI, or related tools.
2. Integrating and testing multiple LLMs (OpenAI, Anthropic, Meta, Gemini, etc.).
3. Setting up retrieval pipelines using vector databases such as Pinecone, Weaviate, or Chroma.
4. Writing Python scripts to automate tasks, call APIs, or handle data pipelines.
5. Experimenting with prompt engineering, tool calling, and model performance tuning.
6. Assisting with deploying prototypes into lightweight production workflows.
7. Documenting experiments, processes, and internal AI workflows.

What You Should Bring

Basic understanding of LLMs, embeddings, RAG, or transformer models.Solid Python skills and familiarity with API calls.Desire to explore agentic frameworks and build end-to-end AI workflows.Curiosity, initiative, and willingness to test ideas quickly.

Extra credit for:

Personal AI projects on GitHubHackathon experienceFamiliarity with FastAPI, Docker, or LangGraphExperience using cloud platforms (GCP/AWS)

Note: This is an unpaid opportunity focused on skill-building, experience, and professional growth.