Senda
Website:
getsenda.com
Job details:
At Senda, we are building a new kind of financial intelligence powered by autonomous AI agents that reason, simulate, and act across complex systems. Our platform enables enterprises to run intelligent, decision-driven workflows and ensuring these systems are reliable, accurate, and production-ready is critical to what we do.
We are looking for an AI Test Architect (5–8 years) to design and own the quality and validation layer for Senda’s platform.
This is not a traditional QA role. You will define how complex AI-driven workflows are tested, validated, and made production-safe across multiple enterprise deployments.
Key Responsibilities
1.Test Architecture & Frameworks
Design and implement end-to-end test frameworks for:
- Agentic workflows (LangGraph-style)
- multi-step decision pipelines
- API + backend systems
- Build automation-first testing systems (not manual test cases)
2.AI / Workflow Validation
Define validation strategies for:
- Reasoning correctness
- workflow integrity
- edge cases and failure paths
- Build evaluation (eval) frameworks for:
- output quality
- consistency
- determinism
3.System Reliability & Edge Case Handling
Identify and test:
- failure modes
- fallback mechanisms
- retry logic
- Ensure robustness in real-world deployment scenarios
4. CI/CD & Production Readiness
- Integrate testing into CI/CD pipelines
- Enable continuous validation before release
- Define quality gates for deployment
5.Collaboration
Work closely with:
- Tech Director (architecture)
- Engineering teams (implementation)
- PM team (use case validation)
- Ensure what is built = what is expected
Required Skills
- 5–8 years in QA / Test Engineering / Automation
- Strong experience in:
- API testing (Postman, REST frameworks)
- Automation (Python preferred)
- Back-end/system-level testing
Experience with:
- cloud-based systems (AWS / OCI / similar)
- CI/CD pipelines (Jenkins, GitHub Actions, etc.)
Preferred / Bonus
Exposure to:
- AI/ML systems or LLM-based workflows
- evaluation frameworks/test harnesses
- data validation/pipeline testing
What We’re Looking For
- Strong system-level thinking (not just test cases)
- Ability to anticipate failure scenarios
- Comfort with ambiguity and evolving systems
- Startup mindset — build, iterate, improve
Why This Role Matters
- You will define how AI systems are made reliable and enterprise-ready.
- Your work will directly impact:
- system correctness
- customer trust
- scalability across institutions
Role Characteristics
- High ownership
- Greenfield problem space
- Direct impact on product + delivery
- Work closely with leadership
📍 Remote | India
Click on Apply to know more.