AI Engineer (LLMs, NLP, RAG, Multimodal AI Systems, Langchain, APIs, Python, AWS)

Responsibilities

• Design and develop AI/ML solutions using LLMs, NLP, and Deep Learning models
• Build and optimize Retrieval-Augmented Generation (RAG) pipelines using vector databases
• Develop and deploy CNN–RNN based architectures for multimodal applications (vision, speech, text)
• Integrate AI models into production systems via REST APIs and microservices
• Develop scalable backend services using Python
• Deploy, monitor, and maintain AI solutions on AWS (or other cloud platforms)
• Build and manage end-to-end ML pipelines, including data ingestion, training, evaluation, and inference
• Optimize model performance for latency, scalability, and cost efficiency
• Collaborate with cross-functional teams to translate business requirements into AI solutions
• Implement CI/CD pipelines for model deployment and continuous integration
• Ensure best practices in model governance, security, and compliance

Requirements

• Strong 3 years of programming experience in Python
• Strong hands-on experience with LLMs (Eg: Claude)
• Experience building RAG pipelines and vector search systems
• Solid understanding of Machine Learning & Deep Learning concepts
• Experience with CNN, RNN, or Hybrid architectures
• Experience in Natural Language Processing (NLP)
• Experience with REST APIs and Microservices architecture
• Hands-on experience with AWS services
• Experience with Docker and CI/CD tools, GitHub, Jenkins
• Experience with frameworks like TensorFlow or PyTorch
• Experience with LangChain, LangGraph, or AI agent frameworks
• Experience with multimodal AI systems
• Experience in data pipelines and distributed systems