Quality Engineering GenAI Platform Architect
Job Profile
Blend of domain expertise in Testing and Quality Engineering with experience and hands on with designing systems over Generative AI technologies for developing and operationalizing use cases across SDLC – STLC.
In this role, the Architect will be responsible for formulating mechanisms to use, deploy Generative AI for multiple use case in Software Testing lifecycle. Formulate architecture patterns for building platform over Generative AI technologies that can automate – orchestrate activities for day in a life of tester. Create the designs for integrations with relevant Testing tools, DevOps pipelines for exchanging inputs and outputs from GenAI engines.
Expertise in LLMs and specific libraries within LLMs with inputs ranging from text, images, media and processing them relevant business logic and produce specific outputs that align with the test flow, test tools in variety of formats – templates that is grounded to the specified context.
Expertise with technology stacks like MEAN, MERN, LAMP and provide guidance, collaborate with development team of Front-end, back-end on building the platform. QE GenAi platform architect will be solely responsible and accountable for operationalizing GenAi for QE use cases with the easy to use wrapper platform for testers delivering in centralized, federated and agile ways of working.
Experience in natural language processing (NLP), model optimization, Fine-tuning language models, Retrieval-Augmented Generation (RAG) techniques, context-aware generation to create comprehensive approach for use cases in testing and quality engineering leveraging the power of embeddings, groundings and vector databases.
Key skills:
Total experience of 7-11 years spanning across domain of Testing – Quality engineering (5+ years), Data science (2+ years) with recent technologies of Generative AI (1+ years) and Design- Architecting hands on (5+ years)
Programming and Scripting: Proficiency in programming languages commonly used in AI and automation, such as Python, Java, or Ruby. Ability to write scripts for test automation and data generation.
Machine Learning and AI: Understanding of generative models and their applications in testing. Knowledge of machine learning frameworks like TensorFlow or PyTorch.
Data Management and Vector Database: Skills in data handling, preprocessing, and manipulation. Proficiency in managing vector databases embeddings, designing and optimizing indexing strategies, efficient retrieval.
Testing and Quality Engineering: Strong background in software testing principles and methodologies. Experience in creating test plans, test cases, and executing manual and automated tests. Familiarity with various testing types, including functional, regression, performance, and security testing.
Test Transformation Consulting: Awareness on understanding the current state and creating roadmap for testing transformation, typical challenges, ways of working, delivery constructs, centralized – federated models of test teams, tools & frameworks for test automation and adjacent areas, shift left, shift right
Industry Domain Testing experience: Understanding of two or more industry or domain for which testing is being performed. Like Banking, Retail, Telecom, Health, Insurance,… Awareness of specific quality and compliance standards relevant to the domain.
Natural Language Processing (NLP): Understanding of NLP concepts and techniques, such as tokenization, part-of-speech tagging, named entity recognition, and sentiment analysis. Familiarity with NLP libraries and frameworks, such as NLTK, spaCy, or Hugging Face Transformers.
Industry LLMs: experience in working with atleast two: ChatGPT, Azure OpenAI, VertexAi, Plam, Llama, Falcon, Hugging face, Sagemaker, … Model Architecture Understanding: In-depth understanding of the generic architecture of LLMs and how it processes and generates language.
Fine-Tuning RAG Models using pre-trained embeddings: Skills in fine-tuning RAG models on specific datasets or domains to improve performance for testing and quality engineering tasks
Contextual Grounding: Ability to ground entities in context, considering the dynamic nature of information and the evolving context.
Ethical and Security, Data Privacy Considerations: Awareness of ethical considerations in AI, including bias mitigation and responsible AI practices and data privacy, security elements
Industry skills:
Pipeline Integration: Proficiency in integrating into existing testing and quality engineering pipelines.
Problem-Solving and Analytical Skills: Ability to analyze complex systems and identify areas for improvement in testing processes. Strong problem-solving skills to address issues related to test automation and generative AI.
Communication Skills: Effective communication to collaborate with cross-functional teams, including developers, QA engineers, and business stakeholders. Ability to communicate complex technical concepts to non-technical audiences.
Continuous Learning: A mindset of continuous learning to stay updated on the latest advancements in AI, testing methodologies, and industry trends.
Collaboration, Teamwork, Documentation, version control: Ability to work collaboratively in a team environment and contribute to a positive and productive work culture. Strong documentation skills for creating and maintaining assets and all documentation. Proficiency in using version control systems (e.g., Git) for tracking changes and managing different versions.
Quality Engineering GenAI Consultant
Job Profile
Blend of domain expertise in Testing and Quality Engineering with experience and hands on with Generative AI technologies as well coding for automation with the key objective of developing and operationalizing use cases across SDLC – STLC.
In this role, the Consultant will be responsible for mapping the STLC, activities – dependencies within STLC, identifying opportunities to brig GenAi in the loop, breaking down the problems into granular chunks, formulating outputs and reverse engineering inputs and analysis mechanisms with GenAI to augment, enhance, automate and orchestrate relevant activities for day in a life of tester and/or in Software Testing lifecycle. Prioritize the use cases for piloting groom the use cases in the client context, with technology and ways of working within the landscape and exploring use of Generative AI technologies that client has subscribed for. Formulate designs for integrations with relevant Testing tools, DevOps pipelines for exchanging inputs and outputs from GenAI engines.
Expertise in LLMs and specific libraries within LLMs with inputs ranging from text, images, media and formulating the business logic, process flow and produce specific outputs that align with the test flow, test tools in variety of formats – templates that is grounded to the specified context.
QE GenAi consultant will be solely responsible and accountable for identifying – enabling and operationalizing use cases with GenAi for testers with well defined inputs – outcomes and business logic for testers delivering across centralized, federated and agile ways of working.
Experience in multiple LLMs and their libraries, Embeddings, Retrieval-Augmented Generation (RAG) techniques, context-aware grounded generation to create comprehensive approach for addressing use cases in testing and quality engineering.
Key skills:
Total experience of 7-11 years spanning across domain of Testing – Quality engineering (5+ years), Test automation – Java – selenium – python (2+ years) with recent technologies of Generative AI (1+ years) and hands on role of Test lead (5+ years) across variety of testing programs and industry domains.
Programming and Scripting: Proficiency in programming languages used for Test automation, Test Automation Framework creation. Ability to write scripts for test automation and data generation and handling test dependencies like mocking.
Data Management and Vector Database: Skills in data handling, preprocessing, and manipulation. Proficiency in managing vector databases embeddings, designing and optimizing indexing strategies, efficient retrieval.
Testing and Quality Engineering: Strong background in software testing principles and methodologies. Experience in creating test plans, test cases, and executing manual and automated tests. Familiarity with various testing types, including functional, regression, performance, and security testing. Having handled complex test programs, integrations with CICD – DevOps pipelines…
Test Transformation Consulting: Awareness on understanding the current state and creating roadmap for testing transformation, typical challenges, ways of working, delivery constructs, centralized – federated models of test teams, tools & frameworks for test automation and adjacent areas, shift left, shift right
Industry Domain Testing experience: Understanding of two or more industry or domain for which testing is being performed. Like Banking, Retail, Telecom, Health, Insurance,… Awareness of specific quality and compliance standards relevant to the domain.
Industry LLMs: experience in working with two or more open source / licensed: ChatGPT, Azure OpenAI, VertexAi, Plam, Llama, Falcon, Hugging face, Sagemaker, … Basic understanding of Model Architecture and how it processes and generates content.
Retrieval augmented generation – RAG: Extensive experience if using RAG models on specific datasets or domains to improve and reference outcomes for testing and quality engineering tasks
Contextual Grounding: Ability to ground entities in context, considering the dynamic nature of information and the evolving context.
Ethical and Security, Data Privacy Considerations: Awareness of ethical considerations in AI, including bias mitigation and responsible AI practices and data privacy, security elements
Industry skills:
Pipeline Integration: Proficiency in integrating into existing testing and quality engineering pipelines.
Problem-Solving and Analytical Skills: Ability to analyze complex systems and identify areas for improvement in testing processes. Strong problem-solving skills to address issues related to test automation and generative AI.
Communication Skills: Effective communication to collaborate with cross-functional teams, including developers, QA engineers, and business stakeholders. Ability to communicate complex technical concepts to non-technical audiences.
Continuous Learning: A mindset of continuous learning to stay updated on the latest advancements in AI, testing methodologies, and industry trends.
Collaboration, Teamwork, Documentation, version control: Ability to work collaboratively in a team environment and contribute to a positive and productive work culture. Strong documentation skills for creating and maintaining assets and all documentation.
Gen AI Automation Testing