Qualifications
Key Responsibilities:Design, develop, and implement applications utilizing Large Language Models (LLMs), both proprietary and open-source. Construct and refine Retrieval-Augmented Generation (RAG) pipelines for more accurate and context-aware outputs. Execute document ingestion, embedding generation, vector search, and ranking systems using cutting-edge vector databases. Fine-tune and assess LLMs for specific domain applications, enhancing their performance and relevance. Collaborate with cross-functional teams, including product management, data engineering, and backend development, to seamlessly integrate AI solutions into production. Develop advanced prompt engineering methodologies and experiment with chaining techniques to improve model responses. Ensure that deployed AI systems are scalable, reliable, and cost-effective. Keep abreast of the latest trends in generative AI, LLM architectures, and retrieval methodologies. Required Skills & Qualifications:2–6 years of direct experience in AI/ML, especially in Natural Language Processing (NLP) and generative AI. Strong grasp of Large Language Models (LLMs) and transformer architectures along with their real-world applications. Demonstrable experience in building RAG-based systems, including knowledge retrieval, embeddings, and using vector databases (e.g., FAISS, Pinecone, Weaviate). Proficient in Python and familiar with machine learning frameworks such as PyTorch, TensorFlow, or Hugging Face Transformers. Experience with prompt engineering, model evaluation, and performance optimization strategies. Knowledge of APIs, deployment frameworks like FastAPI, Docker, or cloud services (AWS, GCP, Azure). Excellent problem-solving abilities with a knack for translating business needs into technical solutions. Preferred Qualifications:Experience with LLM orchestration frameworks like LangChain or LlamaIndex. Understanding of data pipelines and ETL processes for handling large volumes of unstructured data. Familiarity with fine-tuning techniques such as LoRA, PEFT, or instruction tuning.
About the job
weekday-1 is hiring an AI Engineer in Bengaluru, Karnataka, India. This full-time position focuses on building and deploying systems using Large Language Models (LLMs) and Retrieval-Augmented Generation (RAG) methods. The team works on projects that support knowledge discovery, automation, and improved decision-making for clients in different sectors.
What You Will Do
- Design and implement intelligent solutions powered by LLMs and RAG techniques
- Deploy models and systems that help organizations access and use information more effectively
- Work on projects that automate processes and support smarter business decisions
Requirements
- 2–6 years of experience in artificial intelligence or related fields
- Hands-on experience with Large Language Models and Retrieval-Augmented Generation
- Ability to contribute to end-to-end AI system development
About weekday-1
weekday-1 is a cutting-edge technology firm committed to pushing the boundaries of artificial intelligence. Our clients include some of the most innovative companies in the industry, and we pride ourselves on delivering state-of-the-art AI solutions that drive efficiency and unlock new opportunities.