AI Engineer

Role & Responsibilities

Conversational AI & Chatbot Development

• Design and implement intelligent chatbot solutions leveraging advanced Large Language Models (LLMs) such as GPT-4, Claude, and LLaMA.
• Develop sophisticated prompt strategies, conversational chains, and Retrieval-Augmented Generation (RAG) pipelines to ensure contextually relevant and accurate responses.
• Seamlessly integrate chatbot systems with essential APIs, databases, and existing enterprise applications.
• Strategically optimize LLM usage to achieve an optimal balance between operational costs, response latency, and model accuracy.
• Implement robust fallback mechanisms, effective session tracking, and comprehensive context management for natural, multi-turn conversations.
• Uphold the highest standards of secure, ethical, and responsible AI implementation.

AI/ML for Predictive Analytics

• Analyze historical and real-time data to discern critical trends, identify anomalies, and uncover underlying patterns.
• Proficiently work with diverse data types, including structured and unstructured formats such as text, time series, and tabular data.
• Clearly and effectively communicate actionable insights derived from predictive models to stakeholders, ensuring model explainability.

Architecture & Deployment

• Design, build, and maintain scalable AI/ML pipelines and robust infrastructure.
• Utilize MLOps tools (e.g., MLflow, DVC, Airflow, Kubeflow) to automate and streamline model training, testing, deployment, and ongoing monitoring.
• Integrate AI models into production-ready applications via secure APIs and cloud-based ML services.

Qualifications

• Possess 2-4 years of dedicated experience in AI Engineering.
• Demonstrate strong expertise with LLM-based chatbot frameworks like LangChain, LlamaIndex, and Langgraph.
• Exhibit mastery in prompt engineering, embeddings, and transformer-based model architectures.
• Proficiency in Python is preferred, alongside experience in other relevant ML and scripting languages.
• Familiarity with data pipelines, feature stores, and Extract, Transform, Load (ETL) processes is essential.
• Experience working with vector databases such as Pinecone, FAISS, or Weaviate.
• Solid understanding of fundamental machine learning algorithms, statistical principles, and data modeling techniques.