Experience: 3 - 5 years

Work Schedule: 5 days a week

Location: Ahmedabad

Notice Period: Immediate joiners are preferred. (Max. 30 Days)

Key Responsibilities
Design and implement RAG (Retrieval-Augmented Generation) pipelines
Develop AI agents and agentic workflows capable of multi-step reasoning, tool usage, and task automation
Work with embeddings, semantic search, and vector databases
Perform data preparation and basic feature engineering for ML tasks
Develop and deploy machine learning models for prediction/recommendation use cases
Collaborate with product and engineering teams to deliver AI solutions
Monitor and improve model/LLM performance in production

Required Skills:
Generative AI / LLMs
Hands-on experience with LLM APIs (e.g., Open AI, Google, Microsoft Azure AI)
Solid understanding of prompt engineering and evaluation




Experience building RAG systems and working with vector databases (e.g., FAISS, Pinecone, We aviate)
Familiarity with embeddings and semantic search

Programming & ML
Proficiency in Python
Experience with basic machine learning (classification, regression, clustering)
Familiarity with libraries like pandas, NumPy, scikit-learn

Data & Deployment
Positive SQL skills
Experience deploying models or APIs (basic MLOps understanding)
Familiarity with cloud platforms (AWS / GCP / Azure) or Docker

Valuable to Have
Experience with frameworks like LangChain or LlamaIndex
Exposure to production AI systems or real-world deployments
Basic data visualization (Tableau, Power BI, or Python libraries)

📌 Data Scientist Ahmedabad (India)
🏢 ProtocolZone
📍 India