Data Scientist

Tasks

• Build LLM deployment pipelines
• Build RAG pipelines and knowledge bases
• Collaborate on AI projects from exploration to deployment
• Deploy and monitor GenAI solutions
• Develop LLM-powered applications
• Develop generative AI solutions
• Implement evaluation frameworks and prompt versioning
• Optimize prompts and select models
• Support monitoring for model drift
• Use guardrails for responsible AI

Perks/Benefits

• N/A

Skills/Tech-stack

API Development | AWS | Azure OpenAI | Data Preprocessing | Document processing | Elasticsearch | Embedding Generation | Evaluation Frameworks | FastAPI | Fine Tuning | GCS | Git | GitHub | Hugging Face | Jupyter | LLMOps | Langchain | Language Models | Large Language Models | Llamaindex | Milvus | Model Drift | Monitoring | Multi-Modal | Multi-modal Models | OpenAI SDK | Prompt engineering | Python | Qdrant | RAG Architectures | Retrieval-Augmented Generation | Shell Scripting | Text processing | Vector Databases | Vertex AI