Experience : 5.00 + years

Salary : Confidential (based on experience)

Expected Notice Period : 15 Days

Shift : (GMT+05:30) Asia/Kolkata (IST)

Opportunity Type : Hybrid ()

Placement Type : Full Time Permanent position(Payroll and Compliance to be managed by: Z1)

**(*Note: This is a requirement for one of Uplers' client - Z1)

**What do you need for this opportunity?

Must have skills required: Postman/Newman, CI/CD integration, QA, Python, AI / Agentic Testing, Automation Testing, Distributed Systems, Multi-tenant, RAG/vector store exposure

Z1 is Looking for:**** Role : QA Engineer (AI/Agentic Testing) Location - Bengaluru (Hybrid) Own quality across enterprise software, AI, and agentic systems where “mostly works” is not good enough.

About Us We build enterprise AI systems around important business workflows. We bring together models, enterprise data, business context, applications, workflows, and human decisions so the result is secure, observable, governed, measurable, and useful in day-to-day operations.

Lighthouse is the platform accelerator beneath this work. Its independent Context Layer standardizes business meaning, mappings, permissions, evidence, and approved access paths between enterprise data and AI applications, while the wider platform provides connectivity, workflow orchestration, evaluation, governance, and operations. We turn recurring patterns into reusable capabilities without forcing a customer''''''''s data stack, model provider, or workflow into a generic template.

THE ROLE As a QA Engineer, you will own quality across Lighthouse and the production AI systems built on it, from requirements through deployment and ongoing operations. You will test both deterministic software and probabilistic model or agent behavior, working closely with engineering, product, and delivery teams to make systems testable, measurable, secure, and resilient.

This is not a last-step manual testing role: we expect strong automation, exploratory judgment, evaluation design, and the confidence to stop a release when the evidence is not good enough.

What You Will Do

- Design the end-to-end quality strategy for Lighthouse and the AI systems built on it, covering APIs, web experiences, data and context pipelines, agent and workflow orchestration, enterprise integrations, permissions, and deployment paths.
- Build and maintain automated API, integration, contract, UI, and regression suites with meaningful CI/CD quality gates decide what should be validated with deterministic assertions and what requires evaluation-based testing.
- Test agentic behavior beyond happy-path prompts: multi-step reasoning and workflows, tool selection and use, structured outputs,



retrieval and context grounding, state and memory, human approvals, retries, fallbacks, and recovery from partial failure.
- Create evaluation datasets, golden cases, rubrics, thresholds, and error taxonomies for model and agent behavior so prompt, model, context, tool, and workflow changes can be measured before release.
- Actively test high-risk failure modes including hallucinated or unsupported outputs, prompt injection, unsafe tool actions, permission bypass, tenant leakage, malformed inputs, schema drift, rate limits, timeouts, duplicate or delayed events, and degraded upstream systems.
- Validate enterprise integrations and data quality across databases, warehouses, documents, APIs, files, events, and MCP verify authentication, authorization, freshness, provenance, traceability, and behavior under unreliable dependencies.
- Own release readiness, exploratory testing, defect triage, root-cause analysis, and production quality feedback. Turn escaped defects into durable regression coverage and reusable quality standards across projects.

What Success Looks Like

- Releases are backed by evidence and explicit quality criteria rather than a few successful demos or manually selected examples.
- Changes to models, prompts, context, tools, workflows, and integrations are regression-tested against stable datasets and realistic failure scenarios before reaching customers.
- Security, permission, data, workflow, and recovery failures are found before production, and production escapes quickly become automated tests and improved release gates.
- QA increases confidence and release velocity by making quality visible and repeatable instead of becoming a late-stage testing bottleneck.

What You Bring

- 4+ years in QA, test automation, or quality engineering for production software, with strong ownership of backend/API, integration, or enterprise systems from development through release.
- Solid hands-on automation skills in Python, JavaScript/TypeScript, or a comparable language, including API testing, SQL/data validation, test design, and CI/CD integration.
- Experience testing distributed or asynchronous systems involving queues, webhooks, background jobs, retries, idempotency, state transitions, eventual consistency, and failure recovery.
- Hands-on experience testing LLM, AI,



or agentic systems - or strong applied evidence of working with evaluation, grounding, tool use, structured outputs, prompt/model regression, safety, and guardrails.
- Ability to translate ambiguous business workflows into risk-based test scenarios, acceptance criteria, edge cases, and coverage that reflects how real users and enterprise systems behave.
- Strong debugging and collaboration skills: comfortable working with engineers, product and delivery teams, reading logs and traces, reproducing failures, and driving root causes rather than only reporting symptoms.

Useful, But Not Required

- Experience with pytest, Playwright or Cypress, Postman/Newman, contract testing, performance testing, and modern test reporting or observability tools.
- Experience with LLM evaluation or red-teaming tools such as promptfoo, DeepEval, Ragas, LangSmith, or comparable frameworks, plus RAG/vector search and MCP or tool-server testing.
- Experience with security, permission, multi-tenant, accessibility, performance, customer- hosted, private-network, or regulated enterprise deployments.

Why Us

- Treat quality as a first-class engineering discipline and help define how enterprise AI and agentic systems should be tested before the industry has settled on standard answers.
- Work on the difficult correctness boundary where model behavior can be probabilistic but business workflows, permissions, data access, and customer outcomes cannot be casual or opaque.
- Build evaluation, automation, and release-quality capabilities that are reused across Lighthouse, customer workflows, and future AI systems.
- Join a small, ambitious team where QA has real ownership, strong technical partnership, and the authority to challenge or block releases when the evidence is not good enough.

How to apply for this opportunity?

- Step 1: Click On Apply! And Register or Login on our portal.
- Step 2: Complete the Screening Form & Upload updated Resume
- Step 3: Increase your chances to get shortlisted & meet the client for the Interview!

About Uplers: Our goal is to make hiring reliable, simple, and fast. Our role will be to help all our talents find and apply for relevant contractual onsite opportunities and progress in their career. We will support any grievances or challenges you may face during the engagement. (Note: There are many more opportunities apart from this on the portal. Depending on the assessments you clear, you can apply for them as well).

So, if you are ready for a new challenge, a great work environment, and an opportunity to take your career to the next level, don't hesitate to apply today. We are waiting for you!

📌 QA Engineer (Bengaluru)
🏢 Uplers
📍 Bengaluru