Open to opportunities

Rupak Jee kashyap

@rupakjeekashyap

Message

AI Engineer delivering production Generative AI, RAG, and MLOps at scale.

India

Message

What I'm looking for

I’m looking for a role where I can build production-grade GenAI (RAG, vector search) with strong MLOps—low-latency serving, observability, and drift monitoring—to turn prototypes into reliable, scalable AI systems.

I’m an AI Engineer with 1.7 years of experience at Deloitte, specializing in production-grade Generative AI, RAG pipelines, and MLOps. I’ve deployed and scaled LLM-powered applications on Databricks, AWS, and GCP, delivering 99.99% uptime and 200+ production changes with zero rollbacks.

I focus on translating business requirements into reliable, observable AI systems—from prototypes to monitoring in production. On Deloitte, I architected LLM search/recommendation engines (improving retrieval relevance by ~35%), built low-latency serving (<200ms p95), and implemented drift detection and performance monitoring to enable proactive remediation.

Experience

Work history, roles, and key accomplishments

Current

AI Engineering & MLOps Analyst

Current

Deloitte Consulting India

Oct 2024 - Present (1 year 6 months)

Productionized GenAI search and recommendation systems using custom RAG pipelines on Vertex AI, improving retrieval relevance by ~35% and delivering <200ms p95 LLM inference. Implemented end-to-end MLOps on Databricks (Vector Search, Unity Catalog, Delta Lake, MLflow) with drift/performance monitoring, maintaining 99.99% uptime and executing 200+ production changes with zero rollbacks while reduci

Generative AI MLOps MLFlow Vector Search Databricks Unity Catalog AWS

Education

Degrees, certifications, and relevant coursework

Punjab Engineering College (PEC), Chandigarh

Bachelor of Technology (B.Tech), Electrical Engineering

2020 - 2024

B.Tech in Electrical Engineering at Punjab Engineering College (PEC), Chandigarh (2020–2024), with coursework in Machine Learning, Data Structures, and Cloud Computing.