AI Engineer

Job Summary:

We are seeking a highly skilled and motivated AI Engineer with expertise in Python, Large Language Models (LLMs), Prompt Engineering, Vector Databases, and RAG Architecture. The ideal candidate should have a solid foundation in core programming, agentic frameworks, and document/computer vision processing, along with deployment and MLOps capabilities.

Key Responsibilities:

🔹 1. Core Programming & AI Foundations

• Develop and optimize applications using Python and libraries like NumPy, Pandas, FastAPI, etc.
• Apply data structures, algorithms, and object-oriented programming to solve complex problems.

🔹 2. Large Language Models (LLMs)

• Work hands-on with models from OpenAI, Hugging Face, LLaMA, Mistral, etc.
• Perform fine-tuning, prompt-tuning, and explore model internals like attention mechanisms and tokenization.

🔹 3. Prompt Engineering

• Design, test, and optimize prompts (zero-shot, few-shot, chain-of-thought).
• Leverage tools like PromptLayer, LangSmith, or custom frameworks for prompt evaluation and tracking.

🔹 4. Vector Databases

• Integrate and manage vector stores like Pinecone, Weaviate, FAISS, Milvus, or Qdrant.
• Implement embedding generation and similarity search pipelines.

🔹 5. Retrieval-Augmented Generation (RAG)

• Design and implement RAG pipelines using tools like LangChain, Haystack, or LlamaIndex.
• Manage document chunking, embeddings, and retrieval strategies for enhanced LLM outputs.

🔹 6. Agentic Frameworks

• Build intelligent agents using LangChain Agents, LangGraph, or AutoGen.
• Enable multi-step reasoning and autonomous task execution integrated with APIs and tools.

🔹 7. Computer Vision

• Implement image and video processing using OpenCV, YOLO, Detectron2, MediaPipe, or PyTorch/TensorFlow.
• Solve real-world CV tasks like object detection, classification, OCR, or image segmentation.

🔹 8. Document Processing

• Extract structured data from PDFs, invoices, contracts using OCR engines (Tesseract, AWS Textract, Azure Form Recognizer).
• Integrate document pipelines with LLMs for semantic analysis and understanding.

🔹 9. MLOps & Deployment

• Deploy AI models via FastAPI, Streamlit, or Gradio within Docker/Kubernetes environments.
• Maintain CI/CD pipelines and monitor models using tools like MLflow, Weights & Biases, or custom dashboards.

🔹 10. Collaboration & Agile Development

• Work within Agile/SCRUM teams, participate in sprints, planning, and reviews.
• Communicate effectively with stakeholders and contribute to project documentation and open-source initiatives.