Artificial Intelligence Engineer

Company Description GreeneStep is developing AI Agentic automation solutions tailored to Small and Mid Size companies worldwide. GreeneStep AI empowers businesses to modernize the way they engage, support and scale up through intelligent automation and agentic AI solutions. We engineer customizable, enterprise-ready AI agents that integrate seamlessly with existing ERP and CRM systems. Our solutions enhance operations across sales, marketing, service, finance and warehousing - helping teams work smarter, faster and more efficiently. Role Description This is a full-time, on-site role located in Bengaluru for an Artificial Intelligence Engineer. The AI Engineer will design, build, and deploy AI-driven applications that combine machine learning, large language models (LLMs), embeddings, and retrieval-based intelligence using modern tools such as LangChain, FAISS, and FastAPI. The position requires expertise in software development and hands-on implementation of AI technologies to meet project goals. AI Engineer need to work alongside a talented team of software engineers to turn AI research and concepts into scalable, production-ready systems that enhance automation, decision-making, and user experience. Detail Job Responsibilities - Design and Develop AI Systems: - Implement scalable AI services using FastAPI and LangChain, integrating LLMs (OpenAI, HuggingFace, Anthropic, etc.) into production environments. - Build Embedding Pipelines: - Create and optimise text and document embedding workflows using HuggingFace sentence-transformers and FAISS for semantic search and vector retrieval. - Data Processing & Ingestion: - Develop ETL pipelines to process structured and unstructured data (CSV, JSON, PDF, text), ensuring quality and consistency for model consumption. - RAG (Retrieval-Augmented Generation): - Design retrieval-based AI agents that combine contextual data with model reasoning for accurate and explainable responses. - Prompt Engineering & Orchestration: - Create and refine prompts, system templates, and a few short examples to improve LLM responses and prevent hallucinations. - Database Interaction: - Use SQLAlchemy ORM to interact securely with relational databases and manage schema-based contextual data retrieval. - Testing and Validation: - Write unit and integration tests (pytest) for API endpoints, embeddings, and AI pipelines to ensure system reliability. Skills Requirements - Educational Background: - Bachelor's or Master's degree in Computer Science, Artificial Intelligence, Data Science, or a related quantitative field. - Programming Proficiency: - Strong skills in Python are required, including OOP, async/await, and modular programming. - AI/ML Core Knowledge: - Understanding of machine learning algorithms, transformer-based models, NLP, and vector embeddings. Frameworks & Tools: - LangChain or LlamaIndex (LLM integration frameworks) - FastAPI (for API development) - HuggingFace Transformers / SentenceTransformers (for embeddings) - FAISS / Chroma (for vector database and similarity search) - Any Relational database knowledge is required Good To Have: - Experience with OpenAI API, Anthropic Claude, or Gemini. - Familiarity with Docker, Git, pytest, and CI/CD pipelines. - Knowledge of data visualisation tools (Streamlit, Gradio, Plotly). - Exposure to deep learning using PyTorch or TensorFlow. Soft Skills - Strong analytical thinking and problem-solving mindset. - Curious to explore and understand new AI tools and models. - Good communication and documentation skills. - Ability to work both independently and as part of a collaborative AI engineering team.