Key Responsibilities 

ML & LLM Engineering, Search and Recommendation Engines 

• Automate and orchestrate machine learning workflows across major cloud and AI platforms (AWS, Azure, Databricks, and foundation model APIs such as OpenAI) 
• Maintain and version model registries and artifact stores to ensure reproducibility and governance 
• Develop and manage CI/CD for ML, including automated data validation, model testing, and deployment. 
• Implement ML Engineering solutions using popular MLOps platforms such as AWS Sagemaker , MLflow, Azure ML. 
• End-end custom Sagemaker pipelines for recommendation systems
• Design and implement the engineering components of GAR+RAG systems (e.g., query interpretation and reflection, chunking, embeddings, hybrid retrieval, semantic search), manage prompt libraries, guardrails and structured output for LLMs hosted on Bedrock/SageMaker or self-hosted
• Design and implement ML pipelines that utilize Elasticsearch/OpenSearch/Solr, vector DBs, and graph DBs 
• Build evaluation pipelines: offline IR metrics (NDCG, MAP, MRR), LLM quality metrics (faithfulness, grounding), and A/B testing. 
• Optimize infrastructure costs through monitoring, scaling strategies, and efficient resource utilization 
• Stay current with the latest GAI research, NLP and RAG and apply the state-of-the-art in our experiments and systems