Responsibilities
Implement and optimize Retrieval-Augmented Generation (RAG) pipelines to enhance generative model outputs by integrating structured and unstructured data sources for high-relevance, contextual responses
Apply LoRA (Low-Rank Adaptation) and QLoRA (Quantized LoRA) techniques for efficient fine-tuning of large language models, enabling cost-effective training and deployment of personalized or domain-specific AI models
Collaborate with software engineers and Ops teams to deploy ML/AI models into production, ensuring model monitoring, logging, and versioning
Contribute to building and maintaining end-to-end ML pipelines for automation of data ingestion, training, evaluation, and deployment
Collaborate with cross-functional teams to integrate AI solutions into applications.
Stay updated with the latest advancements in AI, ML, and Deep Learning.
A keen interest in learning new technologies and staying updated with the latest trends
Desired Candidate Profile
2+ years of experienced Gen AI developer who has rich programming knowledge, techniques, and methods in the following areas:
LLM Frameworks & Orchestration (LangChain/LangGraph/CrewAI, MCP, RAG)
Vector Databases (Pinecone/Weaviate/Qdrant/Chroma)
Model Deployment & Fine-tuning (vLLM, Ollama, LoRA/QLoRA)
Programming & Databases (Python, Java, SQL)
ML/DL Frameworks (PyTorch, TensorFlow, Hugging Face Transformers)
astro-island,astro-slot,astro-static-slot{display: contents}
