Sr Quality Analyst + Writer

You should have a minimum of 6-8 years of experience in the field. An advanced degree (Masters or higher) in Computer Science, Engineering, or a closely related technical discipline is essential for this role. Your proficiency with Retrieval-Augmented Generation (RAG) techniques and experience working with vector databases such as Weaviate and PineCone will be crucial. Extensive Python programming skills are required, with a proven ability to implement complex solutions. You should have at least 1 year of practical experience in building applications based on Large Language Models (LLMs) using established third-party models like OpenAI and Anthropic. Additionally, you should be skilled in prompt engineering, with experience in crafting function calls and constructing conversational AI applications. Familiarity with advanced LLM techniques such as zero-shot and few-shot learning, as well as fine-tuning for specific use cases, will be beneficial. A strong background in using Generative AI libraries and tools like Langchain and HuggingFace is necessary. You should also have a solid grasp of version control practices, including Git and collaborative development workflows. Comprehensive experience in preparing, managing, and processing extensive datasets, both structured and unstructured, is a must. Proven experience in deploying, scaling, and monitoring machine learning models, particularly LLMs, in live environments is also required. Flexibility to accommodate occasional overlap with US Eastern Time for effective team collaboration is essential, along with professional proficiency in English. Desirable additional experience includes hands-on experience with open-source LLM frameworks such as Llama or Mistral, and prior work involving data in regulated sectors like healthcare or banking. You should be skilled in RESTful API design using Python-FastAPI and development, ensuring secure and scalable interfaces. Proficiency in JavaScript for both front-end and back-end, with a strong command of associated frameworks, is necessary. You should be knowledgeable in architecting scalable solutions using microservices and have experience with the generative AI landscape, specifically around RAG, vector embeddings, LLMs, and open-source AI toolkits. Familiarity with cloud-based infrastructure such as AWS, Azure, and GCP, and their data services is required. Competence in database design and optimization across SQL and NoSQL technologies is essential. Agile development experience, using tools like Git, Jenkins, and Azure DevOps, is preferred. Excellent team collaboration and communication skills, with an aptitude for working across technical and non-technical roles, are also necessary for this role. The three must-haves for this position are Python (4/5), Rest API (4/5), and Generative AI (3/5).,