Senior Generative AI Engineer (LLMs & NLP)

Company Description Crewlogix Technologies has been providing solutions to businesses worldwide since 2000. They specialize in Graphic Designing, software development, Search Engine Marketing, and Sales Strategy to enhance business performance. With a focus on delivering unique user experiences and targeted results, Crewlogix Technologies is a reliable IT development partner offering valuable business insights. Role Description We are seeking a Generative AI Engineer specializing in Large Language Models (LLMs) and Natural Language Processing (NLP) to drive innovation in Agent Development, Retrieval-Augmented Generation (RAG) pipelines, and Chatbot Development. You will be responsible for designing, fine-tuning, and deploying AI-driven solutions that enhance conversational AI capabilities and knowledge retrieval systems. This role requires deep expertise in LLM fine-tuning, prompt engineering, multi-agent architectures, and scalable AI system deployment. You will collaborate with cross-functional teams to build intelligent, context-aware, and scalable generative AI applications. Key Responsibilities

1. Agent Development & Orchestration • Design and develop autonomous AI agents powered by LLMs for real-world applications. • Implement multi-agent collaboration frameworks to improve problem-solving and decision-making. • Optimize agent workflows with prompt engineering, memory management, and reinforcement learning.
2. Retrieval-Augmented Generation (RAG) Pipelines • Architect and implement RAG-based systems to enhance LLM responses with domain-specific knowledge. • Work with vector databases (e.g., FAISS, Weaviate, Chroma, Pinecone) and embeddings to optimize search and retrieval. • Fine-tune ranking and retrieval models for improved document relevance and response quality.
3. Chatbot & Conversational AI Development • Develop and optimize LLM-powered chatbots for enterprise and consumer applications. • Integrate chatbots with APIs, databases, and external knowledge sources to improve contextual understanding. • Implement multi-turn dialogue management, persona-based interactions, and knowledge grounding.
4. Model Training & Optimization • Fine-tune and train open-source LLMs (e.g., LLaMA, Mistral, Falcon, GPT-J) for domain-specific applications. • Optimize model inference for efficiency using quantization (e.g., GPTQ, AWQ) and distillation techniques. • Deploy models on cloud (AWS, GCP, Azure) and edge environments for scalable performance.
5. MLOps & Deployment • Develop scalable and robust AI pipelines for real-time applications. • Deploy and monitor AI models using Docker, Kubernetes, and CI/CD pipelines. • Optimize GPU/TPU usage for cost-effective model inference.

1. Strong experience with LLMs (GPT, LLaMA, Mistral, etc.), NLP, and Generative AI.
2. Experience 2 to 3 years.
3. Hands-on experience with Hugging Face, LangChain, LlamaIndex, OpenAI APIs, or equivalent.
4. Proficiency in Python, PyTorch, TensorFlow, or JAX.
5. Experience in vector search, embeddings, and RAG frameworks.
6. Knowledge of agent-based architectures and multi-agent collaboration.
7. Experience with MLOps, model deployment, and cloud-based AI solutions.
8. Familiarity with RLHF (Reinforcement Learning from Human Feedback) and prompt tuning.

1. Experience with multi-modal AI (text, image, video, speech).
2. Knowledge of knowledge graphs and structured retrieval systems.
3. Contributions to open-source AI projects or research publications.
4. Experience with LLM security, guardrails, and bias mitigation techniques.