Software Engineer in Test

Meril; Gujarat; On-site; INR 800,000 - 1,200,000; Full time

Job summary

A technology company in India is seeking a skilled QA Engineer to ensure the reliability and performance of its AI patent platform. Responsibilities include deep functional testing on Next.js frontend, API validation, and ensuring data consistency across databases. Candidates should have 3–6 years of experience in QA, expertise in testing APIs, and familiarity with LLM frameworks. The role offers the opportunity to work at the intersection of Generative AI and LegalTech in a highly technical environment.

Qualifications

• 3–6 years in QA Engineering, especially in Full-Stack applications.
• Expertise in API testing and understanding Node.js/Python logic.
• Hands-on experience with LLMs, such as OpenAI API or Ollama.

Responsibilities

• Perform deep functional and integration testing on Next.js Frontend.
• Validate REST/GraphQL API contracts and perform multi-user concurrent testing.
• Test CRUD operations and ensure data consistency across databases.

Skills

Full-Stack web applications

Performance testing

Concurrency testing

API testing

Prompt Engineering

Next.js

Database management

Jira/TestRail

Automation frameworks

Tools

Postman

Docker

AWS

GCP

Job description

We are looking for a highly skilled QA Engineer for our (AI Platform) to ensure the reliability, accuracy, and performance of our AI-based patent platform. You won't just follow test cases; you will "break" systems, analyze Next.js code flows, and validate complex LLM agentic workflows. This role requires a unique blend of Full-Stack technical QA (Next.js, APIs, Databases) and AI/LLM testing (RAG, Prompt Engineering, Hallucination detection). You will act as a quality gatekeeper, thinking like a developer to identify architectural flaws before they reach production.

Responsibilities

• Next.js Frontend: Perform deep functional and integration testing. Analyze components, hooks, and state management to identify SSR/CSR edge cases and performance bottlenecks.
• Backend & API: Validate REST/GraphQL API contracts, payload integrity, and authentication flows. Perform multi-user concurrent testing to identify race conditions.
• Database Integrity: Test CRUD operations, transactions, and rollbacks. Ensure data consistency across vector databases (Pinecone/FAISS) and relational schemas.
• AI & LLM Module Validation
• Patent Search & RAG: Validate relevancy ranking, vector search accuracy, and the quality of retrieved context.
• Agent Workflows: Test LLM-powered multi-step agents for autonomy behaviors, "looping" issues, and edge-case handling.
• Model Evaluation: Evaluate outputs for hallucinations, factual accuracy (specifically for patent law), and consistency using tools like OpenAI/Ollama.
• Fine-Tuning Pipelines: Validate datasets and monitor training runs to benchmark model performance.
• Quality Ownership & Engineering
• Code Review: Review frontend and backend code from a testability perspective, identifying anti-patterns and suggesting better error handling.
• Test Design: Write scalable, reusable test cases for complex multi-user workflows.
• Production Readiness: Validate logging, monitoring, and failover recovery. Analyze real-world failure scenarios and production bugs.

Qualifications

• Experience: 3–6 years in QA Engineering, with significant experience in Full-Stack web applications.
• Backend & API: Expert at testing APIs (Postman, curl) and understanding Node.js/Python logic.
• AI Knowledge: Hands-on experience with:
• LLMs: OpenAI API, Ollama, or local model orchestration.
• Vector Tech: RAG pipelines and vector databases (Pinecone, Weaviate, etc.).
• Prompt Engineering: Ability to identify issues with prompts and agentic logic.
• Testing Mindset: Proven ability to test for concurrency, race conditions, and system-level failures.
• Tools: Proficiency in Jira/TestRail and exposure to automation frameworks like Playwright, Cypress, or PyTest. JIRA + Confluence exposure must.

Required Skills

• Familiarity with the Intellectual Property (IP) / Patent domain.
• Experience with Docker, CI/CD pipelines, and cloud platforms (AWS/GCP).
• Experience with LLM evaluation frameworks (e.g., RAGAS, DeepEval).
• Performance/Load testing exposure using tools like k6 or Locust.

Preferred Skills

What We Expect From You

• You are a System Breaker: You don't just test features; you look for ways the system might fail under stress.
• You Think Like a Developer: You can read code to understand where the bugs are likely hiding.
• You are a Quality Advocate: You are comfortable challenging implementations when quality or user experience is at risk.
• You are AI-Curious: You stay updated on the latest in LLMs and agentic frameworks.

Opportunity to work at the intersection of Generative AI and LegalTech. A highly technical environment where QA is treated as an engineering discipline. Freedom to explore and implement new testing methodologies for AI.