Sahil Sharma

Senior Data & AI Engineer @ JLL | GenAI/LLM · Agentic AI (LangChain/LangGraph/Strands, RAG, MCP) | Spark · Kafka · Databricks · Azure · AWS | Python

Bengaluru, Karnataka, India

About

Data & AI Engineer who design & builds production systems on both sides of the stack — the data infrastructure that feeds models, and the agentic AI that runs on top of it. Right now I’m building and leading a team for a multi-modal Agentic AI platform: LangGraph/Strands for orchestration, RAG over CRE data, MCP servers for Tools/Agents, on a FastAPI + React stack deployed on AWS AgentCore & Kubernetes. Before AI, 3.5 years in data engineering: batch and streaming pipelines on Spark, Kafka, Hadoop and Hive feeding data lakes and warehouses, orchestrated with Airflow and Control-M, plus data migrations across AWS, GCP and Azure. I care about the unglamorous parts — data quality, monitoring, and pipelines that don’t page you at 3am. What I do well: — GenAI in production: Azure Foundry/AWS Bedrock Anthropic — LLMs, RAG, prompt engineering, LLM fine-tuning, agentic workflows, MCP — Data engineering: batch/streaming pipelines, Spark, Hive, ETL, data lakes & warehouses, orchestration (Airflow, Control-M) — Languages & data: Python, Scala, advanced SQL; SQL, NoSQL and vector databases — Platform: AWS / Azure, Docker, Kubernetes(AKS/EKS), ECR, CI/CD, microservices & monolith design (HLD/LLD), Terraform, JFrog, ArgoCD

Experience

  • JLL (Full-time · 4 yrs 9 mos)
    • Senior Data Engineer
      Apr 2026 - Present · 3 mos

    • Data Engineer II
      Apr 2024 - Apr 2026 · 2 yrs 1 mo

    • Data Engineer
      Jul 2023 - Apr 2024 · 10 mos

  • Data Engineer at Capgemini
    Oct 2020 - Oct 2021 · 1 yr 1 mo

  • Business Intelligence Analyst at Capgemini
    Jan 2020 - Mar 2020 · 3 mos