Role: Gen AI Developer
Job Type: Fulltime
Shift Timing: UK Time
Location: Pune/Nagpur (Work From Office, Hybrid can be considered)
Job Description:
Roles & Responsibilities
- Maintain and enhance the existing RAG-based Gen AI solution for entity-based query and response.
- Implement and optimize data ingestion, summarization, embedding, and retrieval workflows in Databricks.
- Develop and fine-tune RAG pipelines integrating OpenAI GPT API with embedding models (Ada).
- Configure, maintain, and optimize the Qdrant Vector Database for efficient entity search.
- Manage integration between UI layer (Streamlit chatbot), backend APIs, and Azure Data Lake.
- Create, monitor, and optimize Databricks jobs for data preparation and quality checks.
- Ensure smooth CI/CD deployment of models and applications using Bitbucket/Jenkins.
- Collaborate with Data Ops and Business teams for continuous data quality improvements.
- Troubleshoot and resolve production issues quickly, ensuring minimal downtime.
- Document processes and provide technical knowledge transfer to other team members.
Required Technical Skills
- Programming: Strong Python expertise.
- Gen AI & RAG
- Hands-on experience building Retrieval-Augmented Generation pipelines
- OpenAI GPT API & Embedding models (Ada or similar)
- Prompt engineering and optimization techniques
- Data Engineering: Databricks, Azure Data Lake, PySpark, Pandas, NumPy.
- Vector Databases: Qdrant
- Web/UI Development: Streamlit or equivalent Python-based UI frameworks.
- Deployment & CI/CD: Docker, Bitbucket, Jenkins.
- API Development & Integration: REST API design and integration.
- Cloud & MLOps: Azure environment, model lifecycle management, performance tuning.
- Experience with multimodal RAG (text + image retrieval).
- Familiarity with model explainability tools.
- Knowledge of image processing libraries (OpenCV, PIL) if future scope includes images.
Regards
Vibha Patel
[Confidential Information]
