Senior Software Engineer in Test - Agentic AI
TraceLink · Pune
Company overview:
TraceLink is the world’s largest Agentic Business Network, enabling life sciences and healthcare companies to build and manage a scalable digital workforce of governed, no-code AI agents that execute and coordinate mission-critical supply chain operations alongside human teams. Powered by the Integrate-Once™ OPUS platform, TraceLink links more than 300,000 network participants, enabling multi-enterprise processes at global scale.
Founded in 2009 with the simple mission of protecting patients, today Tracelink has 5 global offices, over 800 employees and more than 1700 customers in over 60 countries around the world. Our expanding product suite continues to protect patients and now also enhances multi-enterprise collaboration through innovative new applications such as MINT.
Tracelink is recognized as an industry leader by Gartner and IDC, and for having a great company culture by Comparably.
Position Overview:
Tracelink is looking for talented full-time software engineers to build products at one of the fastest-growing companies in the Pune area. If you’re self-motivated, intellectually curious, and motivated by designing and developing innovative products for global organizations, you could be a good fit for our team
Who you are:
This is an excellent opportunity to learn and/or extend your knowledge in building large-scale multi-agent systems, define effective strategies for evaluating such systems, and gain hands-on experience in creating and testing non-deterministic software components.
Responsibilities:
The Software Development Engineer in Test assists in building and executing automated tests for the Company's
software products. The SDET will build testing tools to enable automated testing of the TraceLink platform
and application.
Build and execute tests on the Tracelink platform and application.
Build and deploy services for automated testing of the Tracelink platform persistent store.
Execute performance tests on a Distributed Persistent Data store
Create testing tools that can simulate real-world transaction volumes.
Provide high-level analysis to apply appropriate technologies and architecture to solve conceptual problems
Stay curious, build Innovative solution to new age technical issues
Influence designs and decision with supporting data
Work closely with engineers building the core Tracelink product to ensure that testability concerns are factored into the design of the product.
Extend and maintain automation frameworks to enhance Test coverage
Prepare and present clear reports on defect findings that allow developers to reproduce problems and allow the Quality Engineering team to verify that fixes are complete quickly and accurately.
Programmatically interface testing tools with the TraceLink platform and application.
Work closely with engineers building the core TraceLink product to ensure that testability concerns are factored into the design of the product.
Research and remain informed of new technology and tools, and how such technologies could be applied at Tracelink.
Qualifications:
Candidates must possess the following skills and traits:
Bachelor's degree or foreign equivalent in computer science, software engineering, mechanical engineering, or related discipline.
5-8 years of progressive, post-baccalaureate experience in a test automation engineering role involving programmatic interaction with a system under test.
Experience utilizing Java, JavaScript/TypeScript, Eclipse, Ant or Maven, Unix, and an automated unit test framework, such as TestNG.
Experience developing against web services and Web-based APIs.
Experience developing and executing formal test plans, data sets, and test configurations for assigned feature areas.
Helpful skills and experience:
Familiarity with the concepts involved in running cloud-based applications on platforms such as Amazon Web Services.
Experience with the pharmaceutical industry.
Basic understanding of Large Language Models (LLMs) and generative AI systems.
Exposure to testing LLM-based applications, including prompt validation and response evaluation.
Familiarity with multi-agent LLM workflows and coordination patterns (e.g., agent orchestration, tool usage, chaining).
Experience designing test scenarios for AI systems, including edge cases, hallucination detection, and output consistency checks.
Knowledge of evaluation metrics for LLM outputs (e.g., accuracy, relevance, latency, and robustness).
Exposure to automation frameworks or tools for validating AI/ML model behavior.
Please see the Tracelink Privacy Policy for more information on how Tracelink processes your personal information during the recruitment process and, if applicable based on your location, how you can exercise your privacy rights. If you have questions about this privacy notice or need to contact us in connection with your personal data, including any requests to exercise your legal rights referred to at the end of this notice, please contact Candidate-Privacy@tracelink.com.