AI Engineer Intern

AI Engineer Intern

About The Role

• Prototype LLM-driven features – design and test prompts, evaluate model outputs, and iterate quickly.
• Build agentic workflows using LangChain (or similar) to connect language models, tools, and APIs.
• Design & query vector databases (e.g., Pinecone, Weaviate, Chroma) for retrieval-augmented generation (RAG) pipelines.
• Fine-tune / instruct-tune models on domain-specific data to boost performance and reduce hallucination.
• Instrument evaluations—create automated metrics and human-in-the-loop feedback loops to measure quality.
• Collaborate with full-stack & product teams to transform proofs-of-concept into production-ready micro-services.
  

• Solid Python skills and familiarity with modern async/programmatic patterns.
• Hands-on experience experimenting with OpenAI, Claude, Gemini, or similar LLM APIs.
• Practical use of LangChain / LlamaIndex (building chains, agents, tools).
• Comfort with vector embeddings and at least one vector database.
• Basic knowledge of cloud deployment (Docker, serverless functions, or Kubernetes pods).
• Strong problem-solving mindset and an ownership attitude.
  

• Experience fine-tuning models with LoRA or QLoRA.
• Familiarity with streaming speech-to-text / text-to-speech pipelines.
• Exposure to TypeScript or FastAPI for quick backend endpoints.
• DevOps basics: Terraform, CI/CD, monitoring.
  

Note: