AI - Helio for QA

Novature Tech; Chennai District; On-site; INR 1,800,000 - 2,600,000; Full time

Job summary

Novature Tech is seeking a skilled ML/GenAI engineer to architect AI solutions for Quality Assurance and Engineering in Chennai. The role focuses on deploying GenAI/Agentic AI models to automate STLC tasks such as test generation, defect prediction and self-healing, with emphasis on安全, accuracy and governance.

The ideal candidate has 4+ years in analytics and ML in STLC, strong Python and LLM deployment experience, and can lead POCs while collaborating with stakeholders.

Qualifications

• Bachelor’s degree in Statistics, Computer Science, or Engineering
• At least 4 years experience in analytics, data science, ML Engineering in STLC
• Experience with building a range of AI /GenAI/Agentic AI based models into production for use cases like Test case generation, Defect classification & prediction, Root cause analysis (RCA), auto script generation, Model Based Testing (MBT), Test case optimization, Self-healing
• At least 1-2 years of experience in building & deploying LLM based solutions from leading vendors like OpenAI – GPT, Google Gemini or AWS Claude code
• Extensive Python experience required with libraries like LangChain, Ragas, Truelens etc
• Able to communicate technical issues in AI/GenAI with technical & non-technical stakeholders
• Ability to quickly implement POCs on Agentic AI/GenAI assurance use cases based on client data

Responsibilities

• Identify the most effective architectures and models to solve complex data problems around Quality Engineering using GenAI/Ganetic AI
• Apply GenAI/Agentic AI in automating different aspects of STLC such as Test artefact generation, defect prediction, defect triaging, failure analysis, test optimization, impact analysis and self-healing.
• Agentic AI driven Application validation based on RAG/Graph RAG based LLMs to maximize coverage and accuracy
• Validate performance and incorporate feedback function for LLM based applications
• Build solutions to ensure fairness and trustworthiness of GenAI/Agentic AI systems by performing automated tests ensuring prompt safety, and response accuracy
• Lead, mentor, and advise the team members in deploying LLMs and AI models for specified use cases
• Document, summarize and present findings and recommendations for Continuous improvement of AI/GenAI implementations across Quality Assurance & Quality Engineering

Skills

Python programming

LLM deployment

Production AI models

POC development

Stakeholder communication

Agentic AI/GenAI experience

Education

Bachelor's degree in Statistics, Computer Science, or Engineering

Tools

LangChain

Ragas

Truelens

Job description

Responsibilities

• Identify the most effective architectures and models to solve complex data problems around Quality Engineering using GenAI/Ganetic AI
• Apply GenAI/AgenticAI in automating different aspects of STLC such as Test artefact generation, defect prediction, defect triaging, failure analysis, test optimization, impact analysis and self-healing.
• Agentic AI driven Application validation based on RAG/Graph RAG based LLMs to maximize coverage and accuracy
• Validate performance and incorporate feedback function for LLM based applications
• Build solutions to ensure fairness and trustworthiness of GenAI/Agentic AI systems by performing automated tests ensuring prompt safety, and response accuracy
• Lead, mentor, and advise the team members in deploying LLMs and AI models for specified use cases
• Document, summarize and present findings and recommendations for Continuous improvement of AI/GenAI implementations across Quality Assurance & Quality Engineering

Skills / Qualification

• Bachelor’s degree in Statistics, Computer Science, or Engineering
• At least 4 years experience in analytics, data science, ML Engineering in STLC
• Experience with building a range of AI /GenAI/Agentic AI based models into production for use cases like Test case generation, Defect classification & prediction, Root cause analysis (RCA), auto script generation, Model Based Testing (MBT), Test case optimization, Self-healing etc
• At least 1-2 years of experience in building & deploying LLM based solutions from leading vendors like OpenAI – GPT, Google Gemini or AWS Claude code
• Extensive Python experience required with libraries like LangChain, Ragas, Truelens etc
• Able to communicate technical issues in AI/GenAI with technical & non-technical stakeholders
• Ability to quickly implement POCs on Agentic AI/GenAI assurance use cases based on client data