Interested in building and testing LLM-based agents? Banyan Intelligence, an "AI Lifecycle Toolkit for Networks", is hiring an Applied AI/ML Intern for its Engineering team in Bengaluru.
Role Overview
- Company: Banyan Intelligence
- Role: Applied AI/ML Intern
- Department: Engineering
- Location: Bengaluru, India (Hybrid)
- Job type: Internship
- Eligibility: Pursuing a Bachelor's or Master's degree in CS, AI/ML, ECE, or a related technical field
- Stipend and duration: Not mentioned on the posting
Responsibilities
- Build and maintain datasets, evaluation harnesses, and testing pipelines for LLM-based agents
- Prototype AI workflows, RAG pipelines, tool-calling agents, and reasoning chains
- Develop Python and TypeScript services that connect AI inference with backend APIs
- Build ReactJS front-end components for agent dashboards, monitoring, and internal tools
- Containerize services with Docker and automate deployments on Linux
- Help benchmark agents, measure hallucination rates, and improve reliability
- Work with senior engineers on operator constraints, safety logic, and domain playbooks
- Document experiments, model behaviors, and design insights in research notes
- Suggest improvements to prompting strategies, evaluation flows, and system robustness
Requirements
- Strong programming skills in Python and TypeScript
- Experience building UIs or tools with ReactJS
- Understanding of REST APIs, backend development, and integrations
- Familiarity with LLMs, prompt engineering, embeddings, or basic RAG
- Comfort with Linux and Docker
- Ability to break down ambiguous problems and work independently
- Clear written communication and documentation skills
Nice to Have
- LangChain, LlamaIndex, or similar orchestration frameworks
- Inference servers such as Ollama, vLLM, llama.cpp, or cloud endpoints
- Background in information retrieval, vector databases, or search
- Knowledge of model serving, optimization, or fine-tuning
- DevOps, observability, or experiment-tracking tools
- Previous internship experience in AI/ML, backend, or full-stack engineering
