Python Gen AI

We are looking for an experienced Python Engineer with expertise in Generative AI (GenAI) to design, develop, and deploy AI-driven solutions. You ll work with state-of-the-art language models (LLMs), fine-tune open-source models, build scalable AI pipelines, and integrate GenAI capabilities into real-world applications.

Key Responsibilities:

• Design and develop GenAI-based applications using Python and LLMs (e.g., GPT, LLaMA, Mistral, Claude).

• Fine-tune and deploy open-source and proprietary models using frameworks like Hugging Face Transformers, LangChain, or LlamaIndex.

• Build REST APIs and integrate GenAI capabilities into products or internal tools.

• Work with vector databases (e.g., Pinecone, FAISS, Weaviate, Chroma) for RAG (Retrieval-Augmented Generation).

• Develop and manage prompt engineering strategies for various business use cases.

• Implement model evaluation, testing, and observability in GenAI applications.

• Collaborate with data scientists, MLOps engineers, and product teams to productionize GenAI solutions.

• Stay current with the latest research, trends, and tools in the GenAI/LLM space.

Required Skills:

• Strong experience in Python programming.

• Deep understanding of LLMs and Generative AI concepts.

• Hands-on experience with Hugging Face Transformers, OpenAI API, or similar frameworks.

• Familiarity with LangChain, LlamaIndex, or other GenAI orchestration frameworks.

• Experience with prompt engineering and RAG pipelines.

• Knowledge of FastAPI, Flask, or Django for API development.

• Familiarity with Docker, Kubernetes, and cloud platforms (AWS/Google Cloud Platform/Azure) for model deployment.

• Experience working with vector stores and semantic search.

• Good understanding of NLP evaluation metrics and techniques.