Senior Data Scientist
- ๐ฎ๐ณ India
- On-site
- Senior
- 1 month ago
- Machine Learning
- Azure OpenAI
- OpenAI
- GPT
- RAG
- AI
- Databricks
- PySpark
- Vector Search
- Azure AI
- SQL
- Parquet
- CI/CD
- MLOps
- triage
- Azure
- Key Vault
- OData
- Python
- REST API
- Microservices
- LangChain
- Semantic Kernel
- Azure Databricks
- Azure Data Factory
- Azure Synapse
Generative AI Development
Design and develop LLM based applications using Azure OpenAI OpenAI models GPT 4 GPT 4o embeddings etc
Implement prompt engineering RAG Retrieval Augmented Generation and agent based workflows
Build APIs and services to expose Gen AI capabilities to downstream applications
Data Platform Integration
Integrate Gen AI solutions with Azure Data Platforms
oAzure Data Factory ADF
oAzure Databricks PySpark
oAzure Synapse Analytics
oADLS Gen2
Implement vector search using Azure AI Search embeddings
Consume structured and unstructured data SQL Delta Parquet documents
Production Operations
Deploy Gen AI solutions using CICD pipelines
Implement monitoring logging and cost optimization for LLM usage
Work with DataOps MLOps teams to ensure production stability
Support incident triage ICMs related to Gen AI pipelines or services
Security Privacy Responsible AI
Apply Responsible AI principles
oContent filtering
oBias mitigation
oPrompt safety
Ensure compliance with data privacy classifications EUIIEUPI ControllerProcessor
Secure APIs secrets and model access using Azure Key Vault Managed Identity
Collaboration Enablement
Work closely with
oData Engineering teams
oProduct Business stakeholders
oOperations and Support teams
Contribute to documentation KT sessions and best practices
Review and optimize Gen AI solutions for performance and cost
Required Technical Skills
Programming Frameworks
Strong proficiency in Python
Experience with REST APIs and microservices
Familiarity with LangChain Semantic Kernel similar frameworks
Azure AI Stack
Azure OpenAI Azure AI Services
Azure AI Search vector search
Azure Databricks PySpark
Azure Data Factory ADF
Azure Synapse Analytics
ADLS Gen2
Gen AI Concepts
LLMs embeddings tokenization
Prompt engineering techniques
RAG architectures
Agentic workflows
Model evaluation and tuning
Senior Data Scientist ยท LTM