Angshuman Ray — Associate Consultant

With 18+ years across Automation, Enterprise Systems, and Agentic QE specialist, I now specialise in engineering Agentic AI–driven Quality Ecosystems where autonomous systems design, validate, and secure themselves. Led and implemented DeepEval-based evaluation frameworks for Large Language Models (LLMs) and multi-agent AI systems, focusing on reliability, robustness, and production-grade validation. I currently build self-reasoning QE frameworks with Playwright, structured around SKILLS.md (capability mapping layer) and AGENTS.md (role-based agent orchestration layer) — enabling deterministic, reproducible, and auditable AI-driven automation. These systems are powered by Codex 3.5, Gemini 3 Pro Preview, Opus 4.5, Google Antigravity, VS Code + GitHub Copilot, and MCP server architectures. I architect multi-agent systems using CrewAI, AutoGen (Core + gRPC), LangGraph, and Claude MCP — creating workflows where agents plan, execute, evaluate, and self-correct with observability via Langfuse and Braintrust. My specialization extends into secure GraphRAG architectures, integrating Neo4j knowledge graphs with LLM reasoning to build relationship-aware AI systems that are explainable, context-rich, and enterprise-grade. Cybersecurity for me is AI-behavior governance: • Designing secure-by-design autonomous workflows • Implementing structured guardrails and reasoning validation layers • Preventing prompt injection and adversarial agent manipulation • Securing MCP-based orchestration and A2A communication • Embedding trust, traceability, and policy enforcement into LLM systems I bring deep Neo4j expertise from a QE perspective — validating traversal logic, graph integrity, semantic dependencies, and relationship correctness across large-scale healthcare and enterprise ecosystems. Core Focus: • Agentic AI & Multi-Agent Orchestration • Secure GraphRAG (Neo4j + LLMs) • Playwright MCP Automation (AI-Driven QE) • SKILLS.md & AGENTS.md Structured Agent Design • Enterprise LLM Guardrails & Observability • Autonomous Workflow Security Engineering I build AI systems that reason through relationships, validate their own execution, and defend against adversarial behavior.

Stackforce AI infers this person is a Cybersecurity and AI Automation expert with a focus on enterprise solutions.

Location: Kolkata, West Bengal, India

Experience: 18 yrs 10 mos

Skills

Agentic Ai
Playwright Mcp Automation
Playwright Automation
Cybersecurity Governance
Automation Architecture
Automation Engineering
Performance Testing

Career Highlights

Expert in building AI-driven Quality Ecosystems.
Specialized in secure GraphRAG architectures.
Proven track record in Cybersecurity governance.

Work Experience

Wipro

Senior Technical Consultant (2 yrs 11 mos)

Playwright/Cypress Automation and graph database Consultant (1 yr 6 mos)

Cyber Security Consultant (3 yrs 7 mos)

Quantum Inventions (QI)

Automation Lead (2 yrs 6 mos)

Lexmark International, Inc.

Senior Software Engineer Technical Lead (1 yr)

Cognizant Technology Solutions

Automation and Data Engineer (2 yrs 10 mos)

Tata Consultancy Services

Automation Lead (1 yr 4 mos)

Synerzip

QA (1 yr 4 mos)

Tech Mahindra

Performance Engineer (1 yr 10 mos)

Education

B.Tech at West Bengal University of Technology, Kolkata

at Xavier's English School

Angshuman Ray

Associate Consultant

Kolkata, West Bengal, India18 yrs 10 mos experience

Most Likely To SwitchHighly Stable

Key Highlights

Expert in building AI-driven Quality Ecosystems.
Specialized in secure GraphRAG architectures.
Proven track record in Cybersecurity governance.

Stackforce AI infers this person is a Cybersecurity and AI Automation expert with a focus on enterprise solutions.

Contact

Skills

Core Skills

Agentic AiPlaywright Mcp AutomationPlaywright AutomationCybersecurity GovernanceAutomation ArchitectureAutomation EngineeringPerformance Testing

Other Skills

PlaywrightCybersecurityMCPGenerative AI for LeadershipCodex 3.5Gemini 3 Pro PreviewOpus 4.5Google AntigravityREST APIsJIRAApache KafkaGovernanceRisk ManagementBurp SuiteNmap

About

Experience

18 yrs 10 mos

Total Experience

2 yrs 8 mos

Average Tenure

8 yrs

Current Experience

Wipro

3 roles

Senior Technical Consultant

Promoted

Jun 2023 – Present · 2 yrs 11 mos

I currently build self-reasoning QE frameworks with Playwright, structured around SKILLS.md (capability mapping layer) and AGENTS.md (role-based agent orchestration layer) — enabling deterministic, reproducible, and auditable AI-driven automation. These systems are powered by Codex 3.5, Gemini 3 Pro Preview, Opus 4.5, Google Antigravity, VS Code + GitHub Copilot, and MCP server architectures.
I architect multi-agent systems using CrewAI, AutoGen (Core + gRPC), LangGraph, and Claude MCP — creating workflows where agents plan, execute, evaluate, and self-correct with observability via Langfuse and Braintrust.
My specialization extends into secure GraphRAG architectures, integrating Neo4j knowledge graphs with LLM reasoning to build relationship-aware AI systems that are explainable, context-rich, and enterprise-grade.
Cybersecurity for me is AI-behavior governance:
Designing secure-by-design autonomous workflows
Implementing structured guardrails and reasoning validation layers
Preventing prompt injection and adversarial agent manipulation
Securing MCP-based orchestration and A2A communication
Embedding trust, traceability, and policy enforcement into LLM systems
I bring deep Neo4j expertise from a QE perspective — validating traversal logic, graph integrity, semantic dependencies, and relationship correctness across large-scale healthcare and enterprise ecosystems.
Core Focus:
Agentic AI & Multi-Agent Orchestration
Secure GraphRAG (Neo4j + LLMs)
Playwright MCP Automation (AI-Driven QE)
SKILLS.md & AGENTS.md Structured Agent Design
Enterprise LLM Guardrails & Observability
Autonomous Workflow Security Engineering
I build AI systems that reason through relationships, validate their own execution, and defend against adversarial behavior.

PlaywrightCybersecurityAgentic AIMCPGenerative AI for LeadershipPlaywright MCP Automation

Playwright/Cypress Automation and graph database Consultant

Dec 2021 – Jun 2023 · 1 yr 6 mos

Specializing in robust Microsoft Playwright automation for scalable, end-to-end testing. From UI and API flows to multi-user, role-based scenarios and MFA handling — I build reliable test frameworks that catch bugs before users do. Integrating seamlessly with CI/CD, XRAY, and JIRA for full traceability.

playwrightREST APIsCybersecurityJIRAApache KafkaPlaywright Automation

Cyber Security Consultant

May 2018 – Dec 2021 · 3 yrs 7 mos

I worked a a Cybersecurity Consultant for CISCO iOT products. Majorly worked Unity Catalog(databricks) for secure governance of iOT products, Burp, App Scan, Nmap and Rapid 7.

CybersecurityGovernanceRisk ManagementBurp SuiteNmapSplunk+1

Quantum inventions (qi)

Automation Lead

Nov 2015 – May 2018 · 2 yrs 6 mos · Kolkata Area, India

I worked as Automation Architect using Selenium, Cypress, Rest Assured and Appium for Automotive domain.Experienced in automotive cybersecurity with expertise in TLS protocols and TARA methodologies, ensuring secure vehicle systems through robust threat analysis, risk assessment, and encryption standards.

Rest AssureAutomotiveCypress.ioAppiumAutomation Architecture

Lexmark international, inc.

Senior Software Engineer Technical Lead

Nov 2014 – Nov 2015 · 1 yr · Kolkata Area, India

I worked as a Automation Architect for LPM Mobile app using Appium. Also automated the complete web workflow for Lexmark Print Management using Selenium.

AppiumSelenium WebDriverAutomation Architecture

Cognizant technology solutions

Automation and Data Engineer

Jan 2012 – Nov 2014 · 2 yrs 10 mos · Kolkata Area, India

Driving quality with powerful automation using Selenium, REST Assured, and Selenium Grid. From UI to API, I ensure full-stack test coverage with scalable, cross-browser execution. Built to integrate with CI/CD pipelines and deliver reliable, fast feedback across distributed environments.
Uncovering insights through data mining using tools like RapidMiner, Python, and SQL. Experienced in building predictive models, clustering, and classification workflows for business intelligence and decision support. Turning raw data into actionable strategies.

Selenium WebDriverRest AssureRapidMinerAutomation Engineering

Tata consultancy services

Automation Lead

Sep 2010 – Jan 2012 · 1 yr 4 mos · Pune Area, India

Driving quality with powerful automation using Selenium, REST Assured, and Selenium Grid. From UI to API, I ensure full-stack test coverage with scalable, cross-browser execution. Built to integrate with CI/CD pipelines and deliver reliable, fast feedback across distributed environments.

Selenium WebDriverJavaAutomation Engineering

Synerzip

QA

May 2009 – Sep 2010 · 1 yr 4 mos · Pune Area, India

Worked at Synerzip as an Automation and Performance QA Engineer, I specialize in building scalable test frameworks and performance test suites for complex healthcare platforms. My focus is on ensuring reliability, compliance, and efficiency across critical workflows.
Previously, I had the opportunity to work with Kaiser Permanente on their EPR (Electronic Patient Record) system, where I contributed to QA efforts across patient data modules, appointment workflows, and secure data exchange. I successfully cleared HIPAA certification, which deepened my expertise in handling protected health information (PHI) and reinforced my commitment to security and compliance in all testing processes.

HP QuickTest Professional (QTP)JMeterPerformance Testing

Tech mahindra

Performance Engineer

Jul 2007 – May 2009 · 1 yr 10 mos · Pune Area, India

At Tech Mahindra, I worked as a Performance Tester, focusing on SOAP-based service validation and enterprise system performance. My role involved deep testing of backend services using tools such as:
WinRunner – for automated functional and regression testing
Parasoft – to ensure service quality and compliance
SOAPSonar – for comprehensive SOAP protocol testing, especially in service-oriented architectures
I was responsible for designing and executing test scenarios that ensured performance benchmarks were met under real-world conditions, with special attention to service response times, scalability, and reliability across distributed systems.
This role gave me a strong foundation in legacy enterprise tools, middleware testing, and protocol-level diagnostics — critical for ensuring robust backend service delivery.