Senior Data & AI Quality Engineer (Ingestion · Evaluation · Testing)

Title : Senior Data & AI Quality Engineer (Ingestion · Evaluation · Testing)

Experience : 5+ years

Work type : Chennai - Work from Office/ Other Locations - Remote

Employment Type : Full Time

Notice Period : Immediate

Work Day :Mon to Fri

Key Responsibilities :

• •Ingestion pipelines: Confluence, SharePoint/Microsoft 365 (Graph), and repository connectors — parsing, chunking, metadata, incremental sync, data-quality controls
• •Synthetic and non-production data design: corpora shaped to banking IT content (runbooks, incidents, KB articles, change records) with realistic permission structures — the foundation of the cloud-first build
• •The evaluation harness as a product: golden question sets, retrieval precision/faithfulness/citation-accuracy scoring, the zero-leakage permission suite, the zero-unauthorized-actions agent suite; CI-integrated regression gates
• •Performance and load testing with the platform engineer: concurrency profiles, soak tests, degraded-mode behavior
• •UAT orchestration and defect triage across both use cases; acceptance evidence packs per milestone
• •Measurement reporting foundations: the before/after value metrics (time saved per incident, per search) the client's executives receive monthly

Technical Skills :

• •5+ years across data engineering and quality engineering with production Python; you have built pipelines AND the tests that police them
• •LLM evaluation experience: has designed or operated retrieval/generation quality measurement with numeric thresholds (RAGAS-class metrics, custom harnesses, or equivalent) — not just eyeballed outputs
• •Document-processing depth: parsing real enterprise content (tables, permissions, versions, mess), chunking trade-offs, metadata design

• •Test-suite craftsmanship: negative and adversarial test design — the leakage suite is a security artifact, and you think like an attacker when writing it
• •Load/performance testing experience (Locust, k6, or equivalent) and defect-triage discipline

Strongly Preferred :

Synthetic-data generation for regulated domains; Microsoft Graph and Confluence APIs; Milvus/pgvector; Splunk data onboarding; UAT facilitation with business users; banking data-handling standards

About Ampera:

Ampera Technologies, a purpose driven Digital IT Services with primary focus on supporting our client with their Data, AI / ML, Accessibility and other Digital IT needs. We also ensure that equal opportunities are provided to Persons with Disabilities Talent. Ampera Technologies has its Global Headquarters in Chicago, USA and its Global Delivery Center is based out of Chennai, India. We are actively expanding our Tech Delivery team in Chennai and across India. We offer exciting benefits for our teams, such as 1) Hybrid and Remote work options available, 2) Opportunity to work directly with our Global Enterprise Clients, 3) Opportunity to learn and implement evolving Technologies, 4) Comprehensive healthcare, and 5) Conducive environment for Persons with Disability Talent meeting Physical and Digital Accessibility standards.

Skills:- Data engineering and Large Language Models (LLM) tuning