We’re looking for an ambitious AI / LLM / Agentic AI Engineering Intern who’s excited to experiment, build, and ship AI-driven features using the latest in large language models, agentic workflows, vector databases, and automation frameworks.

If you’re the kind of person who stays up way too late tinkering with model prompts, building scrappy prototypes, or trying to make LLMs do things they probably shouldn’t be able to do… you’re exactly who we want.

You’ll work directly with our product and engineering teams to create intelligent workflows, AI agents, and automation systems that actually deliver real-world value — not just cool demos.

Responsibilities:1.Build and prototype AI agents using frameworks like LangChain, LlamaIndex, CrewAI, or similar.

2.Experiment with LLM integrations (OpenAI, Anthropic, Meta Llama, Google Gemini, etc.) to solve real user problems.

3.Design retrieval workflows using vector databases such as Pinecone, Weaviate, Chroma, or FAISS.

4.Build small automation pipelines using Python, APIs, and cloud functions.

5.Work on prompt engineering, prompt optimization, and benchmarking across multiple LLMs.

6.Help move prototypes into production-level features (monitoring, reliability, latency optimization).

7.Contribute to internal tools, model evaluation, data preprocessing, and agentic workflows.

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