Research and prototype LLM-based agent architectures, exploring task decomposition, reasoning, and collaboration between agents
Implement and evaluate proof-of-concept AI systems using open-source or proprietary LLM models and frameworks.
Develop scalable experiment pipelines to assess model behavior, safety, and reliability
Build and optimize Python-based backend components, including prompt chains, vector stores, and evaluation tooling
Integrate prototypes with internal data systems and APIs, simulating realistic enterprise environments
Collaborate with ML engineers and product teams to define success metrics and transition promising prototypes toward production
Document findings in internal research reports, technical memos, and demonstrate the results

Currently pursuing a PhD (3+ years completed) in Computer Science, Machine Learning, AI, or a related discipline
Strong coding and prototyping skills in Python, including familiarity with one or more of: PyTorch, TensorFlow, or similar ML frameworks
LLM agent frameworks (LangChain, LlamaIndex, DSPy, AutoGen, or Semantic Kernel)
Vector databases (FAISS, Chroma, Pinecone, or Milvus)
RAG and retrieval systems using embeddings and knowledge graphs
Deep understanding of LLM internals, including prompting strategies, fine-tuning, and model evaluation
Experience with cloud-based development (AWS) and modern MLOps or LLMOps workflows is an asset
Strong experimental design, data analysis, and communication skills

AI Research Intern, PhD – Full Time, Summer

Key skills