QA Data Science Engineer

Pune, IndiaOn-site

Responsibilities

Validate data contracts, schemas, and API compatibility across services using Pandera , and custom validation rules .
Model behavior validation (input/output ranges, invariants, edge cases) using NumPy, SciPy, and statistical assertions Runtime and performance testing for inference latency, throughput, and resource usage using Locust, k6, or custom load tests .
Integrate ML-specific tests into CI/CD pipelines using GitHub Actions, GitLab CI, or Jenkins, alongside containerized workflows (Docker, Kubernetes).
Implement LLM-specific testing, including: Prompt and response validation, determinism checks, and regression testing using LangSmith .

You will work closely with Data scientists, engineers and product managers to design and optimize AI driven security solutions.
As QA engineer, the ideal candidate has a strong background in Backend engineering, system integrations, ML,AI and data pipelines.
Responsibilities (QA Engineer – Data Science / ML) Establish QA best practices for Traditional ML and Generative AI workflows, including: Functional and regression testing of ML pipelines using pytest and Airflow/ Dagster test utilities and API testing tools (e.g., Postman, pytest-httpx ).
Evaluation of hallucinations, toxicity, and policy adherence using LLM-as-a-judge and /or rule-based checks .
Cost, token usage, and timeout monitoring for GenAI workflows Verify logging, monitoring, and alerting for ML services using Prometheus, Grafana, and cloud-native observability tools.
Requirements: BS or MS in Computer Science or a related field . 2-5 years of
experience in Data or Machine Learning projects . Familiarity and
experience of GenAI applications and tools - PyTorch , LangChain , vLLM etc. Demonstrates a commitment to continuous learning in this rapidly evolving field. Tools listed in the responsibilities section.