About the Company

Zuddl provides a modular platform designed for events and webinars, empowering event marketers to strategically plan and execute events that demonstrably contribute to organizational growth. Trusted by event teams from prominent global organizations including Microsoft, Google, ServiceNow, Zylo, Postman, TransPerfect, and the United Nations, Zuddl offers a flexible and scalable solution. Our modular approach to event management empowers B2B marketers and conference organizers to selectively utilize the specific components required to construct an ideal event experience and effectively scale their overall event program. Zuddl is an outcome-focused platform emphasizing adaptability, functioning more as a strategic partner than a mere vendor.

FUNDING

Having participated in the Y-Combinator program in 2020, Zuddl has successfully secured $13.35 million in Series A funding. This round was led by Alpha Wave Incubation and Qualcomm Ventures, with continued investment from existing partners GrowX ventures and Waveform Ventures.

Job Description

You will be responsible for prototyping innovative, Large Language Model (LLM)-driven features, leveraging frameworks such as LangChain and the OpenAI Agents SDK to enable content automation and intelligent workflow capabilities. A crucial aspect of this role involves developing and optimizing Retrieval-Augmented Generation (RAG) systems, encompassing document ingestion, text chunking, embedding processes utilizing vector databases, and seamless LLM integration. You will actively work with vector databases to implement sophisticated similarity search functionalities, facilitating use cases such as intelligent question-and-answer systems, personalized content recommendations, and context-aware responses. The role demands experimentation with various prompt engineering methodologies and fine-tuning techniques to maximize model performance and relevance. Deployment of LLM-based microservices and intelligent agents will be facilitated through the utilization of Docker, Kubernetes, and industry-standard CI/CD practices. You will systematically analyze model performance metrics, meticulously document findings, and propose data-driven improvements based on thorough quantitative evaluations. Collaboration across various functional teams, including product management, design, and engineering, will be essential to align AI-powered features with overall business objectives and significantly enhance user impact.

Responsibilities

• You will be responsible for prototyping innovative, Large Language Model (LLM)-driven features, leveraging frameworks such as LangChain and the OpenAI Agents SDK to enable content automation and intelligent workflow capabilities.
• A crucial aspect of this role involves developing and optimizing Retrieval-Augmented Generation (RAG) systems, encompassing document ingestion, text chunking, embedding processes utilizing vector databases, and seamless LLM integration.
• You will actively work with vector databases to implement sophisticated similarity search functionalities, facilitating use cases such as intelligent question-and-answer systems, personalized content recommendations, and context-aware responses.
• The role demands experimentation with various prompt engineering methodologies and fine-tuning techniques to maximize model performance and relevance.
• Deployment of LLM-based microservices and intelligent agents will be facilitated through the utilization of Docker, Kubernetes, and industry-standard CI/CD practices.
• You will systematically analyze model performance metrics, meticulously document findings, and propose data-driven improvements based on thorough quantitative evaluations.
• Collaboration across various functional teams, including product management, design, and engineering, will be essential to align AI-powered features with overall business objectives and significantly enhance user impact.

Qualifications

• Demonstrated proficiency in Python programming is essential.
• Candidates should possess hands-on experience with LLMs, including building, fine-tuning, and applying large language models to real-world problems.
• Familiarity with agentic AI frameworks, such as LangChain or the OpenAI Agents SDK, or comparable tools, is required.
• A comprehensive understanding of RAG architectures and documented experience in their implementation through projects or prototypes is necessary.
• Furthermore, practical experience with vector databases, such as FAISS or Opensearch, is expected.
• A portfolio showcasing LLM-based projects, demonstrated through platforms such as GitHub, Jupyter notebooks, or other code repositories, is required to demonstrate practical skills.

Skills

ATS Keywords

Frequently Asked Questions

Other Information

This internship offers a distinct opportunity for conversion to a full-time role, contingent upon performance and organizational needs at the conclusion of the internship period. You will be immersed in a company culture founded on principles of trust, transparency, and unwavering integrity. This role provides a ground-floor opportunity to contribute meaningfully to a rapidly expanding Series A startup. We offer a competitive stipend. You will have the opportunity to contribute to AI-first features within an innovative event-tech startup serving a global customer base. You will thrive in a remote-first, empowering environment characterized by autonomy and mutual trust.

Tags