Looking for a job

Harish Kumar

@harishkumar20

Data & AI Engineer at Avifauna Technology building AWS Bedrock RAG document search with access controls and source references.

United Kingdom

Message

What I'm looking for

I’m open to remote or hybrid roles.

At Avifauna Technology, I built an AWS Bedrock RAG document search solution that answers questions with source references. It uses access metadata so users only see documents they’re allowed to access.

I also handled prompt injection, audit logging and Bedrock Guardrails, with CloudWatch monitoring performance and cost. I’ve worked on RAG designs using Azure OpenAI as well.

At UK Biobank, I built an AWS lakehouse from scratch and took it to production. Kinesis events flowed through Lambda and S3, then Glue and dbt produced research and analytics tables queried through Athena.

At KPMG, I was tech lead on an Azure data platform for a UK university, using Delta Lake layers, Databricks and dbt. Earlier, I supported production data pipelines at UCL and helped move workloads to AWS, later adding Iceberg tables and moving some analytics to GCP.

Experience

Work history, roles, and key accomplishments

Current

Data & AI Engineer

Current

Avifauna Technology

Mar 2026 - Present (7 months)

Working across client projects in data engineering on AWS and GenAI, from requirements through to build, deployment and support. Built a RAG document search solution on AWS Bedrock with access control and monitoring.

AWS Azure OpenAI OpenSearch Lambda AWS ECS API Gateway Python fastAPI Docker Terraform Azure DevOps RAG Cloudwatch

Senior Data Engineer

UK Biobank

Jul 2025 - Feb 2026 (7 months)

Built the AWS lakehouse from scratch and took it to production. Implemented streaming ingestion with Kinesis, Lambda, and Glue, and deployed everything via Terraform and Azure DevOps.

AWS Kinesis Lambda Glue S3 Athena AWS ECS EventBridge IAM Apache Iceberg DBT PySpark Terraform Azure DevOps

Senior Data Engineer

KPMG

Mar 2025 - Jun 2025 (3 months)

Tech lead on an Azure data platform for a UK university, building Bronze, Silver, and Gold layers on Delta Lake. Set up Unity Catalog for access control and lineage, and implemented CI/CD in Azure DevOps.

Azure Databricks PySpark DBT Delta Lake Unity Catalog Data Factory Synapse Azure DevOps

Senior Data Engineer

Avifauna Technology

Oct 2024 - Feb 2025 (4 months)

Built batch and streaming ELT pipelines in Databricks with PySpark. Tuned Delta tables with Z-ordering and liquid clustering, and introduced dbt models and tests on the Gold layer.

Azure Databricks PySpark Spark Streaming DBT Delta Lake Unity Catalog

Data Engineer

UCL (University College London)

Aug 2016 - Sep 2024 (8 years 1 month)

Supported production data pipelines, data warehouse, and cloud infrastructure for around eight years. Migrated workloads to AWS, implemented Kafka streaming, and moved the S3 lake to Iceberg.