Embedding generation – Who Needs Engineers
https://whoneedsengineers.com/wne_live
Software Engineering RecruitmentMon, 07 Oct 2024 16:00:02 +0000en-US
hourly
1 https://wordpress.org/?v=6.6.2https://whoneedsengineers.com/wne_live/wp-content/uploads/2023/06/cropped-wne_logo-3-32x32.pngEmbedding generation – Who Needs Engineers
https://whoneedsengineers.com/wne_live
3232AI/ML Engineer
https://whoneedsengineers.com/jobs/emerging-technologies-and-specialized-roles/ai-ml-engineer-5/
Mon, 07 Oct 2024 16:00:02 +0000https://whoneedsengineers.com/wne_live/jobs/jobs-categories/ai-ml-engineer-5/AI/ML Engineer
Job Description:
We are looking for a skilled AI/ML Engineer to join our dynamic team, focusing on the design and development of innovative generative AI solutions. This role emphasizes the creation and optimization of applications that utilize large language models (LLMs), Retrieval-Augmented Generation (RAG) systems, and vector databases. You will collaborate with various teams, including data scientists and engineers, to effectively deploy generative AI technologies that tackle real-world challenges. The successful candidate will be responsible for developing efficient data embedding pipelines, managing vector storage solutions, implementing RAG frameworks, and fine-tuning LLMs to align with diverse project requirements. Additionally, your contributions will extend to enhancing AI system security, optimizing performance, and developing user-friendly query interfaces.
IT Languages:
Python
JavaScript
TypeScript
As an AI/ML Engineer, you will undertake a variety of responsibilities aimed at harnessing the power of generative AI technologies.:
Generate embeddings for unstructured data and manage storage in vector databases like ChromaDB or Pinecone.;; Automate processes to ensure embeddings are continually updated with new data.;; Experiment with various embedding models to determine the most effective options for each project.;; Develop natural language query interfaces that integrate LLMs with both structured and unstructured datasets.;; Implement dynamic prompting techniques and function calling to enhance query handling capabilities of LLMs.;; Design and maintain a QA backend for interaction with vectorized data.;; Implement RAG systems to improve response accuracy by using relevant context from retrieved data.;; Classify and route queries appropriately between structured and unstructured data sources.;; Utilize frameworks like LangChain or LlamaIndex to manage workflows effectively.;; Fine-tune and optimize LLMs for various use cases, continuously testing and refining model performance.;; Monitor system performance and optimize for scalability and efficiency while adhering to security protocols.
Spoken Languages:
English;; German;; French
Skillset:
Large language models
Embedding generation
Vector databases
Retrieval-Augmented Generation
Natural language processing
Machine learning frameworks
Cloud services
Containerization
Soft Skills:
Strong problem-solving abilities
Effective communication skills
Ability to collaborate in cross-functional teams
Qualifications:
Master’s Degree in Computer Science, Data Science, Mathematics, Statistics, or a related field
Strong mathematical or statistical background preferred
Experience with large language models such as GPT or LLaMA
Proficiency in embedding generation and managing vector stores
Years of Experience:
5
Location:
United States
Job Benefits:
Health insurance
Retirement savings plan
Paid time off
Professional development opportunities
Flexible working hours
Working Conditions:
Full Time
Employment Type:
Permanent Contract
Company Culture:
The company fosters a culture of innovation and collaboration, encouraging team members to explore new ideas and technologies. A supportive environment is created where employees are empowered to take initiative and contribute to meaningful projects.
Opportunities For Advancement:
Career growth within the AI/ML field, Access to training and development programs, Opportunities to lead projects