Prototype and integrate LLMs (OpenAI, Azure OpenAI, Anthropic, etc.) into web services, apps, and workflows.
Support the design and development of intelligent chatbots and autonomous agents using cutting-edge GenAI technologies to support content analysis, content gap identification, content summarization and like activities.
Implement and optimize RAG (Retrieval Augmented Generation) systems to provide accurate information retrieval and contextual responses
Write prompt chains, system prompts, and structured outputs (JSON/XML/Markdown) for reliable responses.
Build evaluation harnesses: test sets, metrics, and A/B experiments.
Develop, manage, and deploy intelligent AI agents to include knowledge retrieval (RAG), allowing interaction with external APIs, databases, and applications.
Develop connectors and RAG pipelines.
Use open-source platforms for debugging, testing, and monitoring generative AI applications.
Implement guardrails and safety (content and safety filters, PII scrubbing, hallucination detection, policy enforcement).
Contribute to backend services (Python/TypeScript) and micro-APIs to operationalize AI features.
Write observability hooks: logging, tracing, prompt/version tracking, feedback loops.
Collaborate on model selection and cost/performance tradeoffs (latency, throughput, token cost, quality).
Document prompt patterns, playbooks, and API usage; share learnings in reviews/demos.

Bachelor’s in CS/Engineering or equivalent experience (internships count)
0–2 years building software (internships count)
Hands-on with at least one: Python (FastAPI, Flask) or TypeScript/Node (Express, Next.js)
Familiarity with LLM APIs (OpenAI/Azure OpenAI/Anthropic) and prompt engineering basics
Experience with Git, RESTAPIs, and CI/CD concepts
Basic knowledge of cloud (AWS desired, Azure acceptable) and containers (Docker)
Strong communication and curiosity
Must be legally authorized to work in the United States without the need for employer sponsorship, now or at any time in the future

AI Intern

Key skills