Build and deploy intelligent applications using Machine Learning and Generative AI technologies.
Work with Large Language Models (LLMs) such as: - OpenAI
- Azure OpenAI
- Claude
- Gemini
Design and develop Retrieval-Augmented Generation (RAG) systems.
Develop scalable APIs using: Perform machine learning model training, inference, and evaluation.
Work on prompt engineering for optimizing LLM outputs.
Build and manage AI pipelines using frameworks such as: - LangChain
- LlamaIndex
- LangGraph
- CrewAI
Handle structured and unstructured datasets using: Work with embeddings and vector search implementations.
Integrate vector databases such as: - Pinecone
- FAISS
- Weaviate
- Chroma
Collaborate with teams to integrate AI capabilities into real-world applications.
Use cloud and deployment tools for scalable AI solutions.
Maintain code repositories and development workflows using Git and Jupyter Notebook.
Requirements
Strong programming skills in Python.
Basic understanding of JavaScript / TypeScript (preferred).
Experience in API development using FastAPI or Flask.
Good understanding of: - Machine Learning fundamentals
- Model training and inference
- Feature engineering
- Model evaluation metrics
Hands-on experience working with LLM APIs such as: - OpenAI
- Azure OpenAI
- Claude
- Gemini
Knowledge of: - Prompt Engineering
- Retrieval-Augmented Generation (RAG)
Experience with AI/LLM frameworks: - LangChain
- LlamaIndex
- LangGraph
- CrewAI
Strong data handling skills using Pandas and NumPy.
Understanding of embeddings and vector search concepts.
Experience with SQL and vector databases.
Basic knowledge of cloud platforms: Familiarity with Docker, REST APIs, Git, and Jupyter Notebook.
Passion for AI/ML and building scalable AI-powered applications.