AI Engineer

About the role

Design, develop, and optimize robust RAG (Retrieval-Augmented Generation) pipelines to facilitate effective information retrieval in conversational AI systems. Build and deploy intelligent AI agents capable of handling multi-turn conversations, executing autonomous tasks, and managing tool invocation based on user intent.

Key responsibilities

• Model Development & Ownership: Design, develop, and optimize robust RAG (Retrieval-Augmented Generation) pipelines to facilitate effective information retrieval in conversational AI systems.
• AI Agent Deployment: Build and deploy intelligent AI agents capable of handling multi-turn conversations, executing autonomous tasks, and managing tool invocation based on user intent.
• System Integration: Implement and maintain a Model Context Protocol to ensure seamless, standardized connectivity and data sharing between AI systems, external APIs, and databases.
• Data Architecture: Manage and optimize vector databases and advanced indexing techniques to efficiently store and retrieve contextual data.
• LLM Optimization: Fine-tune large language models (LLMs) and apply advanced prompt engineering techniques to optimize for specific product use cases.
• NLP/NLU Implementation: Implement powerful NLP, NLU, and NLG techniques (sentiment analysis, entity recognition, text generation) to enhance product capabilities.
• Continuous Improvement: Stay abreast of the latest ML and AI advancements, proactively suggesting new tools or frameworks to improve the tech stack.
• Cross-Functional Collaboration: Partner with product and engineering teams to translate AI capabilities into practical, scalable applications.

Requirement

• Degree in Computer Science, Artificial Intelligence, Machine Learning, or a related field.
• 3+ years of industry experience in machine learning engineering, with a strong focus on building and deploying conversational AI or NLP solutions.
• Proven, hands-on experience developing RAG models, working with vector databases (e.g., Pinecone, Milvus, Weaviate), prompt engineering, and utilizing LLMs.
• Strong, production-level programming skills in Python and proficiency with ML frameworks such as PyTorch, TensorFlow, or JAX.