Teams at LeewayHertz

Build and operate production Generative AI systems, including LLM applications, RAG pipelines, agentic workflows, evaluation harnesses, model serving, and inference optimization. Own AI components end to end, from retrieval and model integration through deployment, monitoring, and cost governance. Lead technical direction, conduct reviews, mentor engineers, prototype emerging techniques, and collaborate with product, architecture, and client stakeholders on enterprise AI delivery.

Own end-to-end architecture and delivery of enterprise Generative AI solutions, including RAG, agentic workflows, LLM integration, evaluation, observability, security, and compliance. Lead model and platform selection, define scalable reference architectures, support pre-sales and client workshops, guide multiple delivery teams, mentor engineers, govern technical decisions, and remain hands-on with prototypes and production code. Balance cost, latency, accuracy, security, and business value across concurrent client engagements.

Designs, builds, and maintains scalable cloud data platforms and production pipelines across Azure, Databricks, Snowflake, and SAP. Responsibilities include ingestion, ETL/ELT, Lakehouse and dimensional modeling, CI/CD with Databricks Asset Bundles and Azure DevOps, data quality and observability, performance optimization, documentation, and stakeholder collaboration. The role also includes technical architecture, client advisory, engineering leadership, mentoring, and delivery of production Generative AI systems.