AI Engineer - RAG & Large Language Models

This role is for one of the Weekday's clients

Salary range: Rs 1800000 - Rs 3000000 (ie INR 18-30 LPA)

Min Experience: 2 years

Location: Bangalore

JobType: full-time

We are seeking a highly motivated AI Engineer with 2–6 years of experience to join a growing team working at the forefront of applied AI. In this role, you will design and build intelligent systems powered by Large Language Models (LLMs) and Retrieval-Augmented Generation (RAG). You will play a key role in developing scalable, production-grade AI solutions that enhance knowledge discovery, automation, and decision-making across various domains.

Key Responsibilities:

• Design, develop, and deploy applications leveraging Large Language Models (LLMs), including both proprietary and open-source models
• Build and optimize Retrieval-Augmented Generation (RAG) pipelines for accurate, context-aware responses
• Implement document ingestion, embedding generation, vector search, and ranking systems using modern vector databases
• Fine-tune and evaluate LLMs for domain-specific use cases, improving performance, accuracy, and relevance
• Collaborate with cross-functional teams including product, data engineering, and backend teams to integrate AI solutions into production systems
• Develop prompt engineering strategies and experiment with chaining techniques to enhance model outputs
• Ensure scalability, reliability, and cost-efficiency of deployed AI systems
• Stay updated with the latest advancements in generative AI, LLM architectures, and retrieval techniques

Required Skills & Qualifications:

• 2–6 years of hands-on experience in AI/ML, with a strong focus on NLP and generative AI
• Solid understanding of Large Language Models (LLMs), transformers, and their real-world applications
• Proven experience in building RAG-based systems, including knowledge retrieval, embeddings, and vector databases (e.g., FAISS, Pinecone, Weaviate)
• Proficiency in Python and experience with ML frameworks such as PyTorch, TensorFlow, or Hugging Face Transformers
• Experience with prompt engineering, model evaluation, and performance optimization techniques
• Familiarity with APIs and deployment frameworks such as FastAPI, Docker, or cloud platforms (AWS, GCP, Azure)
• Strong problem-solving skills and the ability to translate business requirements into technical solutions

Preferred Qualifications:

• Experience with LLM orchestration frameworks such as LangChain or LlamaIndex
• Understanding of data pipelines, ETL processes, and handling large-scale unstructured data
• Exposure to fine-tuning techniques such as LoRA, PEFT, or instruction tuning
• Knowledge of search systems, semantic search, and hybrid retrieval methods
• Prior experience deploying AI systems in production environments