AI Engineer

Crewlogix Technologies is looking for an AI Engineer specializing in Large Language Models (LLMs) and Natural Language Processing (NLP) to propel innovation in Agent Development, Retrieval-Augmented Generation (RAG) pipelines, and Chatbot Development. In this role, you design, fine-tune, and deploy AI-driven solutions that enhance conversational AI capabilities and knowledge retrieval systems. Your deep expertise in LLM fine-tuning, prompt engineering, and scalable AI system deployment is critical as you collaborate with cross-functional teams to build intelligent, context-aware, and scalable generative AI applications.

This position primarily involves developing autonomous AI agents powered by LLMs for real-world applications and implementing advanced multi-agent collaboration frameworks for enhanced problem-solving. You will also architect and implement RAG systems that enrich LLM responses and contribute to the development of optimization tools for chatbots. As part of our innovative team, you will have opportunities to apply your skills in model training, optimization, and deployment strategies, ensuring robust AI solutions that meet our business needs.

Responsibilities

Design and develop autonomous AI agents powered by LLMs to address practical challenges in various domains.
Implement multi-agent collaboration frameworks that facilitate enhanced problem-solving and decision-making among agents.
Optimize AI agent workflows utilizing prompt engineering, memory management techniques, and reinforcement learning approaches.
Architect and implement Retrieval-Augmented Generation (RAG) systems, integrating them with domain-specific knowledge for improved LLM responses.
Utilize vector databases (such as FAISS, Weaviate, Chroma, Pinecone) to enhance search and retrieval processes and optimize performance with embeddings.
Fine-tune ranking and retrieval models to improve document relevance and the quality of responses generated by LLMs.
Develop and optimize LLM-powered chatbots tailored for enterprise and consumer applications, focusing on usability and user satisfaction.
Integrate chatbots with various APIs, databases, and external knowledge sources to enhance contextual understanding and user interaction.
Implement multi-turn dialogue management and persona-based interactions, ensuring chatbots engage users effectively across various scenarios.
Fine-tune and train open-source LLMs such as LLaMA, Mistral, Falcon, and GPT-J for specific application requirements.
Utilize optimization techniques like quantization and distillation to improve model inference efficiency, particularly on resource-constrained environments.
Deploy AI models across cloud services (AWS, GCP, Azure) and edge environments, ensuring scalable and efficient performance.
Develop MLOps pipelines for managing and monitoring AI models effectively in real-time applications.
Utilize tools like Docker, Kubernetes, and continuous integration/continuous deployment (CI/CD) strategies to streamline deployment processes.
Optimize GPU/TPU utilization for cost-effective model inference and scalable AI solutions.