Hi, I'm

Suresh

Sureshkumar Mahalingam

Lead AI Engineer & AWS Solutions Architect

I ship production AI agents and RAG systems on AWS, and the data platforms they run on.

Days -> Min Plain-English leadership analytics on Bedrock and LangGraph. Companion RAG cut research time about 50%.
2.2h -> 36m Nightly sync of nearly 600 SQL Server tables. Recurring failures brought to zero.
77K requests Production RAG on AgentCore that drafts work orders from historical service requests.

Technical stack

AI - Cloud - Delivery

Agentic AI

LangChain LangGraph Bedrock Agents AgentCore AWS Strands CrewAI AutoGen n8n RAG (FAISS / Pinecone) MCP LangSmith NL-to-SQL

ADLC

Agent-first Architecture Multi-agent Orchestration Human-in-the-loop AI Guardrails Agentic CI/CD Responsible AI Cost Governance

Cloud & AI Platforms

AWS Bedrock Amazon Textract Lambda API Gateway S3 / CloudFront DynamoDB Step Functions Glue ECS Fargate Athena / Redshift CDK (TypeScript) IAM / STS cdk-nag

Languages

Python PySpark TypeScript Go Java

Backend / Frontend

Next.js React NestJS Spring Boot GraphQL REST APIs

DevOps & Data

Terraform Docker GitLab CI/CD Apache Spark PostgreSQL DuckDB

Projects

Professional

Days -> Min

Multi-Agent NL Analytics

LangGraph and Bedrock answer plain-English questions with Athena SQL over S3.

Companion RAG cut research time about 50%. A direct partnership with leadership expanded the team.

LangGraph Bedrock Athena S3

77K requests

Production AgentCore Agents

Two agents on AgentCore and Strands: an NL-to-SQL API other teams call, and RAG over 77K service requests.

Drafts work orders. A verified-answer loop raises accuracy without retraining.

AgentCore Strands RAG Claude

2.2h -> 36m

Nightly SQL Sync

Nearly 600 tables, cloud to on-prem SQL Server, on Step Functions and ECS Fargate.

Row-count verification. Recurring failures brought to zero.

Step Functions ECS Fargate SQL Server

3h -> 15m

Data Validation

Config-driven PySpark and DuckDB across S3, PostgreSQL, Redshift, and Iceberg.

Estimated 30-50% lower run cost. A Next.js dashboard cut troubleshooting 60-80%.

PySpark DuckDB Iceberg Next.js

539 / day

7Rs Lake Migration

Legacy SQL Server landed daily as S3 Parquet, Athena, and Glue.

Automated drift reports replaced manual reconciliation.

PySpark Athena Glue S3

70% less compute

Operations Platform

Six Spring Boot services and Next.js on ECS Fargate and Aurora PostgreSQL.

Engagement up 30%. Load times down 20%. Scheduled shutdown cut non-production compute about 70%.

Spring Boot Next.js ECS Fargate Aurora

Personal