Tcs Hiring For AI Tester

Tata Consultancy Services Limited; India; Remote; INR 900,000 - 1,500,000; Full time

Job summary

Tata Consultancy Services Limited in PAN India seeks an AI Tester to lead QA and validation of AI/ML and LLM-based web apps across PAN India. You will ensure performance, reliability, and data integrity while aligning with GMP requirements.

Responsibilities include designing test plans, executing functional tests, validating models and prompts, and collaborating with product, development, and business teams to drive quality across AI features and regular website components.

Qualifications

• QA/validation experience, preferably with AI/ML systems.
• Strong knowledge of AI concepts (LLMs, evaluation metrics, drift).
• Experience in API testing, SQL/data validation, website/UI testing, and test design.
• Strong analytical skills.
• Experience in checking application logs using log aggregation tools.

Responsibilities

• Design and execute functional testing including edge cases, prompt variations, bias validation, and LLM behavior
• Create test plans and test strategies
• Experience with bug tracking and test case management tools
• Collaborate with stakeholders -product, development, and business teams
• Test AI chat features along with regular website components
• Validate model quality, evaluation metrics, drift detection, and performance
• Test RAG, retrieval accuracy, grounding, and agent/tool-use scenarios
• Conduct non-functional testing (performance, reliability, security)
• Support test documentation and audit/compliance activities
• Work with product, development, and platform teams on test planning and defect resolution
• Testing AI models against hallucinations, conducting advanced prompt testing, and ensuring that all AI applications adhere strictly to Good Manufacturing Practices (GMP) and data integrity standards.
• Design testing suites and datasets to identify, measure, and mitigate factual, logical, and structural hallucinationsin Generative AI systems.
• Model Validation:Conduct rigorous data-drift and concept-drift analysis on models.
• Prompt Evaluation:Systematically test and benchmark system prompts to ensure consistent, highly deterministic outputs for complex workflows.
• Vulnerability Testing:Perform robust vulnerability and adversarial prompt testing to protect internal AI applications from malicious exploits or unexpected behavior.

Skills

QA testing

AI/ML concepts

API testing

SQL validation

Data validation

Analytical thinking

Python

TypeScript

Tools

Log aggregation tools

Bug tracking tools

Test case management tools

Job description

Job Title: AI Tester

Location: PAN India

Responsible for QA and testing of AI/ML and LLM based web applications, ensuring performance, reliability and compliance.

Key Responsibilities

• Design and execute functional testing including edge cases, prompt variations, bias validation, and LLM behavior
• Create test plans and test strategies
• Experience with bug tracking and test case management tools
• Collaborate with stakeholders -product, development, and business teams
• Test AI chat features along with regular website components
• Validate model quality, evaluation metrics, drift detection, and performance
• Test RAG, retrieval accuracy, grounding, and agent/tool-use scenarios
• Conduct non-functional testing (performance, reliability, security)
• Support test documentation and audit/compliance activities
• Work with product, development, and platform teams on test planning and defect resolution
• Testing AI models against hallucinations, conducting advanced prompt testing, and ensuring that all AI applications adhere strictly to Good Manufacturing Practices (GMP) and data integrity standards.
• Design testing suites and datasets to identify, measure, and mitigate factual, logical, and structural hallucinationsin Generative AI systems.
• Model Validation:Conduct rigorous data-drift and concept-drift analysis on models.
• Prompt Evaluation:Systematically test and benchmark system prompts to ensure consistent, highly deterministic outputs for complex workflows.
• Vulnerability Testing:Perform robust vulnerability and adversarial prompt testing to protect internal AI applications from malicious exploits or unexpected behavior.

Requirements

• 37 years in QA/validation, preferably with AI/ML systems
• Good knowledge of AI concepts (LLMs, evaluation metrics, drift)
• Experience in API testing, SQL/data validation, website/UI testing, and test design
• Strong analytical skills
• Experience in checking application logs using log aggregation tools

Preferred

• Hands-on experience with GenAI/LLM testing and prompt engineering
• Knowledge of Python/ Typescript for test automation
• Exposure to GxP/regulated environments
• Experience in pharmaceutical or biotechnology industry
• Knowledge of Responsible AI practices