2 days ago
Bengaluru, India or Hyderābād, IndiaStaff+
Responsibilities
- Architect and scale RAG pipelines that process unstructured IT logs and documentation into vector embeddings.
- Maintain high-performance vector database infrastructure and optimize retrieval for agentic reasoning workflows.
- Build knowledge graphs, semantic layers, metadata-driven ELT frameworks, reusable pipeline templates, and data-quality frameworks.
- Create automated guardrails to identify noise, bias, PII, and other data-quality issues before data reaches models.
- Develop, deploy, and maintain production data infrastructure and associated pipeline automation.
- Apply performance tuning, partitioning, incremental processing, schema evolution, and large-volume data-processing techniques.
- Support healthcare data requirements including patient identity, effective dating, PHI handling, lineage, and auditing.
Requirements
- 7+ years of experience in data engineering or data warehousing.
- 4+ years of hands-on experience with Databricks/Spark and Snowflake.
- Advanced hands-on experience with Databricks, Python, SQL, Spark/PySpark, Delta Lake, and Snowflake.
- Strong experience with Databricks Workflows/Jobs, notebooks, Unity Catalog, Git, and CI/CD.
- Experience building metadata-driven ELT frameworks, reusable pipeline templates, data-quality frameworks, reconciliation utilities, and automated testing.
- Knowledge of dimensional and normalized data modeling, troubleshooting, debugging, and root-cause analysis.
- Experience with healthcare data, including patient identity, effective dating, PHI handling, lineage, and audit requirements.
- Preferred: experience with GenAI/RAG applications, agentic AI, generative AI, LLMs, prompt engineering, embeddings, vector search, MLflow, AI/ML lifecycle practices, enterprise LLM platforms, agent frameworks, and productionizing AI solutions.
- Preferred: healthcare domain experience and familiarity with PHI-sensitive datasets.
Benefits
- Hybrid-friendly work culture.
- Professional certifications and qualifications, including learning opportunities involving Microsoft, Google, and Amazon.
- Be Well programs supporting financial, mental, physical, and social health.
- Personalized development goals, coaching, continuous feedback, and career-path tools.
- Opportunities to grow into other technical or non-technical roles.
Tech Stack
Categories
Data Engineering
About Kyndryl
Kyndryl is a public IT services company that designs, runs, and modernizes mission-critical infrastructure for large enterprises and governments. Spun off from IBM in 2021, it is headquartered in New York City and trades on the NYSE (ticker: KD). The company provides managed infrastructure, cloud migration and operations across AWS, Azure, and Google Cloud, plus mainframe, network, security, data, and digital workplace services.
