SAMARTH MEHRA / TORONTO, CANADA

AI × Cloud.

Building intelligent systems.
From model to infrastructure.

I build intelligent AI systems and the cloud infrastructure that powers them. I bring 3+ years of experience across software engineering, generative AI, APIs, and cloud automation.

mehrasamarth9@gmail.com
FROM MODEL TO INFRASTRUCTURE01–03

Intelligence grounded in context. Tools built for reuse.

3+

Years in software engineering

70%

Less processing time · AWS Batch

50%

Faster database reads and writes

50%

Lower human support load

4

Junior engineers mentored · Tech Mahindra

01 / SELECTED WORK

Intelligence, engineered.

AI applications and cloud automation, built end to end. Explore the decisions behind the systems.

PDF → CHUNKS → EMBEDDINGSChromaDB retrievalLangChain / BedrockRetrieved context → Citation-backed answer
01 / RAG APPLICATION

DocuMind

Intelligent Document Q&A System

From a PDF to a grounded answer: a document intelligence platform with semantic retrieval, citation-backed responses, and reusable MCP tools.

LangChainAWS BedrockChromaDBHuggingFaceFastAPIReactMCPLoRA / QLoRA
QUERY → SEARCHEvaluate evidenceRefine & retry ↺Sufficient evidence → Source-backed briefing
02 / AUTONOMOUS AGENT

NewsBot

Autonomous News Research Agent

Research that checks its own work: an agent that searches, evaluates, refines, and synthesizes current information into source-backed briefings.

LangGraphFastAPITavily SearchGPT-4o miniMCP
EVENT-DRIVEN PROCESSING
S3 File arrivalAWS Batch Docker jobDynamoDB State tracking
Terraform / IaC · Infrastructure provisioning
Jenkins CI/CD · ECR container images
03 / CLOUD AUTOMATION · TECH MAHINDRA

AWS Batch Automation

Event-Driven Data Processing Pipeline

From manual file handling to automated processing: an AWS workflow connecting S3 events, containerized Batch jobs, and DynamoDB state tracking, delivered through Jenkins CI/CD.

AWS BatchS3Docker / ECRDynamoDBJenkins CI/CDPythonTerraformIaC
02 / THE INTERSECTION

The application.
And everything
underneath.

I’m a software engineer working at the intersection of AI applications and cloud infrastructure.

My work spans production RAG systems, autonomous agents, MCP integrations, backend APIs, AWS infrastructure, containers, CI/CD, and database migration. I connect the model’s capabilities to the engineering needed to deploy and operate the system.

IDEA → AI APPLICATION → API
INFRASTRUCTURE → DEPLOYMENT → MONITORING
03 / ENGINEERING CAPABILITIES

One connected skill set.

Explore each layer to see how application intelligence connects to infrastructure.

Cloud Engineering

I built AWS Batch automation with S3 event triggers, Dockerized jobs, and DynamoDB state tracking. Manual data-processing automation reduced processing time by 70%.

S3 ingestion

An uploaded file triggers the processing workflow, removing manual file detection.

Select a delivery or infrastructure technology to explore its role.

Batch delivery

Cloud infrastructure experience

Additional cloud skills

AWS CDKKubernetes
ECR

Stores the Docker images used by the AWS Batch processing jobs.

AI Engineering

My AI engineering work spans retrieval pipelines, agents with conditional routing, and reusable MCP tools. Explore the capability map below.

Application / FastAPI

React interfaces and FastAPI endpoints connect users to backend AI capabilities.

Generative AILoRA / QLoRALLMOpsPrompt engineeringMulti-agent systems
04 / EXPERIENCE

Built through delivery.

Software engineering across Canada and India, with practical systems and measurable outcomes.

2024–2026

New Delhi, India

Individual Design

Software Engineer

  • Designed and deployed an AWS-hosted customer support chatbot using RAG, LangChain, and the OpenAI API, reducing incoming human chat load by 50% with context-aware answers.
  • Led 3 engineers in migrating a legacy, human-dependent chatbot to an autonomous AI system, reducing escalations from 80% to 20% and cutting average response time.
  • Implemented intelligent routing that hands queries to human agents when they fall outside model confidence.
  • Extended the chatbot with end-to-end order checkout, enabling purchases directly within the chat interface and reducing checkout drop-off.
  • Architected and maintained AWS infrastructure with Terraform for the production support platform, supporting high availability, scalable deployment, and backend integration.
  • Integrated the platform with backend payment and order-processing systems to support reliable end-to-end transactions.
2022–2024

Toronto, Canada

Tech Mahindra

Software Engineer

  • Automated manual data-processing workflows with AWS Batch, reducing processing time by 70%; demonstrated the solution directly to the client, leading to production adoption.
  • Led a 3-engineer team to build an AWS Batch automation system with S3 event triggers, DynamoDB state tracking, and Dockerized jobs, eliminating manual intervention.
  • Used Python to generate and configure AWS resources and delivered the Batch system through Jenkins CI/CD.
  • Migrated the production database from Oracle to PostgreSQL, improving read/write performance by 50% and reducing storage overhead through database administration and performance tuning.
  • Automated infrastructure provisioning at Tech Mahindra using Infrastructure as Code (IaC) with Terraform. Provisioned and configured EC2 instances and supporting AWS resources, standardizing environment setup and reducing manual configuration overhead.
  • Configured VPC networking, security groups, and IAM permissions for least-privilege access; set up CloudWatch monitoring and alerts to surface infrastructure health issues.
  • Rebuilt a legacy customer-facing interface with React, JavaScript, HTML5, CSS3, and OAuth, delivering a responsive experience that increased user engagement by 30%.
  • Mentored 4 junior engineers through hands-on sessions on AWS services and database migration, accelerating onboarding and strengthening team delivery.
05 / TOOLKIT

Depth across the stack.

Technologies and capabilities from my AI and cloud engineering experience.

AI & LLM engineering

Agentic AILangGraphLangChainLangSmithRAG pipelinesMCPLLM fine-tuningLoRA / QLoRAOpenAI APIHuggingFace TransformersPrompt engineeringMulti-agent systemsSemantic searchFAISSChromaDBLLMOps

Cloud & infrastructure

AWSEC2S3DynamoDBECRAWS BatchAWS BedrockCloudWatchIAMVPCSecurity groupsAWS CLIAWS SDKAWS CDKTerraformInfrastructure as Code (IaC)Infrastructure monitoringInfrastructure automationGCPAzure OpenAI Service

DevOps & containers

DockerKubernetesJenkinsCI/CDGit

Programming & APIs

PythonJavaJavaScriptSpring BootFastAPIReactREST APIsHTML5CSS3

Databases & systems

PostgreSQLMySQLMongoDBOracle → PostgreSQL migrationPerformance tuningPowerShellIAM & access controlNetworking

Collaboration & delivery

OAuthTechnical documentationCross-functional communicationCustomer supportService deskTeam leadershipMentoring
06 / CERTIFICATIONS

Foundations that matter.

AWS Certified Cloud Practitioner

Amazon Web Services

HashiCorp Certified: Terraform Associate

HashiCorp

07 / EDUCATION

An engineering foundation.

Centennial College

Advanced Post-Graduate Diploma
Software Engineering Technology
Toronto · 2021

Guru Nanak Dev University

Bachelor of Technology
Computer Science and Engineering
Punjab · 2019

LET’S CONNECT

Let’s build something
intelligent.

I’m interested in AI and Cloud Engineering opportunities where I can build scalable intelligent systems, from the application layer to infrastructure.