Senior AI Testing Engineer

VidvanConnect Software Solutions Pvt. Ltd.; Delhi; On-site; INR 1,800,000 - 3,000,000; Full time

Job summary

VidvanConnect Software Solutions Pvt. Ltd. is seeking a Senior AI Testing Engineer to own quality across Generative AI products and platform.

With 5-8 years in software testing and at least 2-3 years in GenAI, you will design evaluation frameworks, build automated testing pipelines, and define what constitutes good LLM outputs. You'll work with AI engineers and product teams to ensure reliable, safe systems and measurable improvements over time.

Qualifications

• 5-8 years in software testing, QA engineering, SDET or test automation.
• 2-3 years hands-on testing of GenAI/LLM systems.
• Strong Python-based test automation experience.
• Experience with API, integration and performance testing.

Responsibilities

• Design and own testing strategies for GenAI products and AI systems.
• Build automated evaluation pipelines and CI/CD-integrated testing.
• Define quality KPIs, governance, and standards for GenAI applications.
• Collaborate with AI engineers, product, and platform teams to embed quality.
• Create datasets and benchmark suites for GenAI evaluation.

Skills

Test automation

API testing

Performance testing

Quality metrics

Observability

GenAI knowledge

Tools

Python

LangSmith

Ragas

TruLens

OpenAI Evals

LangChain evaluation tools

Job description

We are looking for a Senior AI Testing Engineer to own quality across our Generative AI products and platform. Experience 5-8 years total experience in software testing, QA engineering, or SDET roles, with at least 2-3 years of meaningful, hands-on exposure to Generative AI systems, LLM applications, or AI quality engineering.

This role is fundamentally about engineering quality into AI systems - not running test scripts. You'll design evaluation frameworks, build automated testing pipelines, and define what "good" looks like for LLM outputs, RAG systems, AI agents, and voice AI applications. You'll work directly with AI engineers and product teams to make sure our systems are reliable, safe, and measurably improving over time.

If you understand how LLMs fail, know how to catch hallucinations before users do, and want to build the quality infrastructure that underpins production AI at scale - this is the role.

Key Responsibilities-

• Design and own comprehensive testing strategies for Generative AI products - including LLM applications, RAG pipelines, AI agents, voice AI systems, and workflow automation
• Define evaluation methodologies covering functional testing, response quality, hallucination detection, safety and guardrail testing, prompt injection, bias and toxicity, retrieval quality, latency benchmarking, and agent workflow validation
• Build reusable AI testing frameworks and automation pipelines for continuous evaluation
• Create datasets, benchmark suites, and golden test sets for GenAI evaluation

Automated Evaluation

• Develop automated evaluation pipelines using LLM-as-a-Judge and hybrid evaluation methods
• Implement CI/CD-integrated AI evaluation pipelines
• Drive observability and monitoring strategies for production AI systems

Quality Standards & Collaboration

• Define measurable quality KPIs for AI systems
• Establish testing standards, best practices, and governance processes for GenAI applications
• Work closely with AI engineers, product, and platform teams to embed quality throughout the development lifecycle

Required Skills & Experience-

• 5-8 years in software testing, QA engineering, SDET, or test automation
• 2-3 years of hands-on experience testing or evaluating production-grade Generative AI or LLM-based systems
• Strong test automation skills in Python
• Experience designing scalable automated testing frameworks
• Familiarity with API testing, integration testing, and performance testing

Generative AI Knowledge

• Solid understanding of how LLM systems work - and how they fail
• Experience with RAG architectures, prompt engineering, AI agents, embedding models, and vector databases
• Understanding of LLM evaluation methodologies and AI system failure modes

GenAI Testing Frameworks

• Hands-on experience with at least one or more GenAI evaluation frameworks, such as: DeepEval, Ragas, LangSmith, Promptfoo, TruLens, OpenAI Evals, or LangChain evaluation tools

Quality Engineering

• Expertise in test strategy, test planning, test automation architecture, defect lifecycle management, and quality metrics
• Ability to define and track measurable quality KPIs for AI systems

Preferred Qualifications-

• Experience with cloud platforms (AWS, Azure, or GCP)
• Familiarity with MLOps / LLMOps workflows
• Experience with CI/CD pipelines and DevOps practices
• Exposure to monitoring and observability tooling for AI systems
• Understanding of security and compliance for GenAI products
• Experience with conversational AI or voice AI systems