AI Intern

As a Gen AI FDE Intern, you will be on the front lines of the AI revolution. You will work directly with our Clients and Internal Teams to transition Gen AI from "cool demo" to "mission-critical production system." You will be responsible for building, tuning, and deploying LLM-powered applications (Agents, RAG systems, and Copilots) that solve specific business workflows.

Key Responsibilities

• RAG Architecture: Design and implement robust Retrieval-Augmented Generation (RAG) pipelines.
• Prompt Engineering & Tuning: Iterate on sophisticated prompt templates and leverage techniques like Chain-of-Thought (CoT) or ReAct to improve model reliability for specific client use cases.
• Evaluation Frameworks: Build "LLM-as-a-judge" or manual evaluation benchmarks to measure the accuracy, latency, and "hallucination" rates of deployed models.
• Integration & Orchestration: Use internal CWIC frameworks built on top of  LangChain to glue together LLMs with customer-specific APIs and data sources.
• Client Education: Help non-technical stakeholders understand the limitations of LLMs (e.g., stochastic nature) while demonstrating their transformative value.

Required Skills & Qualifications

• AI/ML Foundations: Deep understanding of transformer architectures, tokenization, and the difference between fine-tuning and RAG.
• Python Mastery: High proficiency in Python, as it is the lingua franca of the AI ecosystem.
• Data Engineering: Ability to clean and preprocess unstructured data (PDFs, HTML, SQL tables) for high-quality embedding.
• API Design / MCP Servers: Experience building and consuming RESTful APIs to integrate AI features into existing enterprise software.

Bonus Points

• Experience with Guardrails (e.g., NeMo Guardrails) to ensure AI safety and compliance.
• Familiarity with Model Quantization or local LLM deployment (e.g., Ollama, vLLM).
• Active contributions to open-source AI projects or a portfolio of "Agentic" side projects.