3 days ago
Bengaluru, India or Coimbatore, IndiaMid Level / Senior
Responsibilities
- Own assigned AI agents and services through requirements, design, development, testing, deployment, monitoring, maintenance, and operational support.
- Diagnose and improve existing codebases, prompts, tool integrations, and data pipelines while adding regression coverage and preserving working capabilities.
- Build and improve AI agents for test authoring, review, execution, and failure analysis using tool calling, structured outputs, workflow state, retries, and human review.
- Develop and integrate Model Context Protocol clients, servers, and tools with Playwright automation, approved knowledge sources, and engineering workflows.
- Deliver maintainable UI and API automation using Python, PyTest, and Playwright, and review agent-generated tests for coverage and reliable execution.
- Evolve RAG ingestion, chunking, metadata, retrieval, source attribution, and knowledge-graph modeling and retrieval integration.
- Evaluate agent behavior and output quality, track retrieval relevance and regressions, and investigate failures using operational and test data.
- Integrate agents and automation suites with CI/CD and scheduled execution, and support QE teams through scenario clarification, test data preparation, documentation, demonstrations, and troubleshooting.
- Apply secure handling of credentials, enterprise data, and tool permissions while delivering incrementally and communicating risks early.
Requirements
- 4–6 years of relevant software engineering or test automation engineering experience in a SaaS product organization.
- Strong Python programming skills, including API integration, asynchronous programming, debugging, modular design, automated testing, Git, and code review.
- Hands-on experience building, deploying, and maintaining LLM-based AI agents with tool integrations, workflow orchestration, failure handling, and evaluation.
- Practical Playwright, Python, and PyTest automation experience covering fixtures, stable locators, waits, test data, UI and API validation, and CI execution.
- Hands-on Model Context Protocol integration experience, including tool schemas, authentication, permissions, error handling, and execution boundaries.
- Practical RAG implementation experience and working knowledge of knowledge graphs, entity and relationship modeling, and graph-based retrieval.
- Experience deploying and supporting containerized services and CI/CD, with working knowledge of cloud environments, secrets management, configuration, and observability.
- Ability to take ownership of unfamiliar systems, deliver under tight deadlines, balance support with planned work, and collaborate with QE and engineering teams.
- Preferred: experience maintaining automation frameworks, reducing flaky tests, modernizing legacy automation, or converting manual scenarios into automated tests.
- Preferred: familiarity with vector or hybrid search, graph databases, agent orchestration and evaluation tools, or Kubernetes.
Benefits
- The role is part of a global organization with teams and operations across India, North America, the United Kingdom, and Australia.
- AppViewX is an Equal Employment Opportunity Employer.
Tech Stack
Categories
About AppViewX
AppViewX builds enterprise software for automated certificate lifecycle management, PKI, and machine identity security delivered as SaaS and on‑premise. Its AVX Platform discovers and governs digital certificates and non‑human identities, automates renewals and access controls, and helps large organizations prove compliance. Founded in 2008 and headquartered in New York, the company is privately held with backing from Haveli Investments and is used by enterprises across financial services, healthcare, and technology.