Quality Assurance Engineer (AI, Agents & Automation)
Join us and contribute to the discovery of medicines that will impact lives!
About Aganitha
Accelerate drug discovery and development for Biopharma and Biotech R&D with in silico solutions leveraging Computational Biology & Chemistry, High throughput Sciences, AI, ML, HPC, Cloud, Data, and DevOps.
In silico solutions are transforming the biopharma and biotech industries. Our cross-domain science and technology team of experts embark upon and industrialize this transformation. We continually expand our world-class multi-disciplinary team in Genomics, AI, and Cloud computing, accelerating drug discovery and development. What drives us is the joy of working in an innovation-rich, research-powered startup bridging multiple disciplines to bring medicines faster for human use. We are working with several innovative Biopharma companies and expanding our client base globally. Read about how and what solutions we build.
Aganitha (अगणित): “countless” or “limitless” in Sanskrit serves as a reminder and inspiration about the limitless potential in each one of us. Come join us to bring out your best and be limitless!
Role Overview
At Aganitha, we are looking for a Quality Assurance Engineer to work at the intersection of AI systems, agents, and test automation.
This role goes beyond traditional QA — you will be responsible for validating AI-driven workflows, agent-based systems, and complex product behaviors, ensuring reliability, robustness, and scalability in production environments.
Key Responsibilities
- Design, develop, and maintain automation frameworks and test suites
- Test and validate AI/LLM-powered systems and agent-based workflows
- Evaluate end-to-end behavior of autonomous agents, including multi-step reasoning and decision flows
- Identify and debug failure modes, hallucinations, edge cases, and inconsistencies
- Build test strategies for dynamic, non-deterministic systems
- Collaborate with engineering, AI, and product teams to ensure high-quality releases
- Contribute to scalable QA strategies for AI-first products
Ability to clearly explain:
- Automation frameworks used or built
- End-to-end testing approach
- Handling of failures and edge cases
- Strong practical experience over theoretical knowledge
- Ability to think beyond traditional QA and test AI-driven, adaptive systems
Required Qualifications
- Strong hands-on experience in automation testing (mandatory)
- Experience with automation tools/frameworks such as Selenium, Playwright, Cypress, or similar
- Proven experience in end-to-end testing of real-world applications
- Ability to design scalable and maintainable automation frameworks
- Strong problem-solving skills with focus on edge cases and system behavior
Preferred Qualifications
- Exposure to AI/LLM-based systems, prompt testing, or agent frameworks
- Understanding of testing non-deterministic systems and AI outputs
- Experience with product-level QA in complex systems