Gen AI Engineer

Role & responsibilities

Role Overview:

1. Generative AI Development

• Build and fine-tune generative AI models for text, code, or multimodal outputs.
• Implement prompt engineering and optimization techniques for better model performance.

2. RAG (Retrieval-Augmented Generation)

• Design and integrate RAG pipelines to enhance LLM responses with external knowledge sources.
• Work with vector databases (e.g., Pinecone, Weaviate, FAISS) and embedding models for efficient document retrieval.

3. LLM Integration

• Deploy and customize large language models (OpenAI, Hugging Face, Azure OpenAI, etc.).
• Optimize inference performance and scalability for production environments.

4. Python Development

• Write clean, efficient Python code for AI workflows, APIs, and automation scripts.
• Develop data preprocessing, model training, and evaluation pipelines.

5. Architecture & Deployment

• Design end-to-end AI solutions integrating LLMs, RAG, and backend systems.
• Deploy models on cloud platforms (Azure, AWS, GCP) and containerized environments (Docker, Kubernetes).

6. Collaboration & Documentation

• Work closely with data scientists, ML engineers, and product teams.
• Document processes, best practices, and maintain code repositories.

• Strong understanding of

  GenAI concepts

   and

  LLM architectures

   (Transformers, attention mechanisms).
• Hands-on experience with

  RAG frameworks

   and

  vector search technologies

  .
• Proficiency in

  Python

   and libraries like

  LangChain

  ,

  Transformers

  ,

  FastAPI

  ,

  Pandas

  ,

  NumPy

  .
• Familiarity with

  cloud services

   and

  MLOps practices

  .
• Knowledge of

  embedding models

  ,

  tokenization

  , and

  prompt engineering

  .