// Deloitte Consulting · Ottawa, ON · 10+ Years

Aditya S.
Chandramohan

AI Systems Quality Lead · Quality Engineering Leader · Test Architect

GCP Professional ML Engineer GCP Generative AI Leader Azure Solutions Architect Expert ISTQB Adv. Test Manager TMMi Professional Secret Level II Clearance

10+ years architecting enterprise testing solutions across financial services, healthcare, government, and security. From GenAI validation at a Fortune 100 healthcare org to owning $450K automation programs — I deliver quality at scale.

View Projects Get In Touch

// 01. about

About Me

I'm a Senior Quality Engineering Leader and Test Architect at Deloitte Consulting, currently serving as QA Lead for a strategic programme at a top-5 Canadian bank — leading a distributed team across Poland and India. Prior to this, I led a 14-member cross-functional team delivering production-grade agentic AI quality assurance for a Fortune 100 healthcare organization's CCaaS platform deployed to 500+ agents.

My background spans financial services, healthcare, government, and cybersecurity. I've owned $450K automation programs, authored enterprise non-functional test plans for systems processing 50K+ daily transactions, and pioneered event-driven testing methodologies that reduced production incidents by 65%. On the AI side, I design evaluation frameworks for LLMs, RAG pipelines, and agentic systems — defining metrics for relevance, accuracy, and helpfulness and establishing human annotation programs to close the feedback loop.

With certifications across AI/ML (GCP, AWS), cloud architecture (Azure, GCP), and quality leadership (ISTQB, TMMi) — and an active Secret Level II clearance — I bring both the strategic depth and hands-on execution that senior quality roles demand.

🏆
INDUSTRY AWARD
North American Software Testing Award — Best Use of Technology in Project (2022).
⚡
30,000+ HRS SAVED
Led $450K automation program delivering 30,000+ hours in annual productivity gains across 30 regression runs.
👥
TEAMS UP TO 15
Led cross-functional teams across Canada, Poland, India — financial services, healthcare, government.
📐
TEST ARCHITECT
Microservices, event-driven, NFT, GenAI — framework design and test strategy across every layer.

// 02. skills

Technical Skills

🤖 GenAI & AI Testing
LLM Evaluation Agentic AI Testing RAG Evaluation AI Red-Teaming Human-in-the-Loop AI Judges Human Annotation Programs Prompt Engineering Testing AI Observability Claude AI Google Vertex AI GitHub Copilot LangChain OpenAI SDK
📐 Test Architecture & Strategy
Test Strategy Authorship Framework Architecture Shift-Left Testing CI/CD Quality Gates Non-Functional Testing Disaster Recovery Testing Performance Engineering Security Testing BDD / TDD Microservices Testing Event-Driven Architecture Testing
🎯 CCaaS & Contact Center QA
Genesys Platform Testing Multi-Channel QA (Voice, Chat) Conversational AI Testing Agent Assist Validation HIPAA-Compliant Validation PII Handling Verification Real-Time Transcript QA
⚙️ Automation & Tooling
Selenium Playwright TestComplete Cypress Spock Rest Assured JMeter BrowserStack UiPath Burp Suite SonarQube Jenkins Azure DevOps
☁️ Cloud & DevOps
GCP (ML Engineer) Azure (Arch Expert) AWS (AI Practitioner) Docker Kubernetes Kafka gRPC / Protobuf PostgreSQL Cassandra Grafana
💻 Languages
Python Java JavaScript Groovy SQL
👥 Quality Leadership
Team Leadership (15+ engineers) $450K+ Budget Ownership Vendor Coordination Stakeholder Management Quality Governance Quality Metrics & KPIs Go/No-Go Decision Making AI Adoption Enablement
🏛️ Domain & Compliance
Financial Services Healthcare (HIPAA) Federal Government Cybersecurity (IBM QRadar) Responsible AI AI Risk Management Secret Level II Clearance

// 03. projects

Personal Projects

FEATURED PROJECT

llm-eval-toolkit

A modular Python toolkit for evaluating large language models in production settings. Covers faithfulness, answer relevance, context precision, and hallucination detection with support for RAGAS and DeepEval backends. Designed for CI/CD integration and enterprise RAG pipeline validation.

Python RAGAS DeepEval LangChain Pytest GitHub Actions
↗ GitHub
$ python run_eval.py --suite rag
# Running RAG evaluation suite...
 
✓ Faithfulness 0.94
✓ Answer Relevance 0.91
✓ Context Precision0.88
⚠ Hallucination 2 flagged
 
# Report: eval_report_2025.html
✓ 47 passed · 2 warnings

// 04. contact

Get In Touch

I'm always open to discussing AI/ML quality engineering challenges, consulting opportunities, or interesting open-source collaborations. Whether you have a specific project in mind or just want to connect — reach out.

✉ Email Me LinkedIn GitHub