Custom Software Engineer
Accenture
Hyderabad2–5 yrs2h agovia Naukri
About the Role
Project Role: Custom Software Engineer
Key Responsibilities
- AI Native Data Product Engineering (on Datasphere)
- Design and implement governed data products using Datasphere concepts (Spaces, shareable models/views).
- Build semantic models fit for analytics and AI consumption.
- Retrieval + Grounding (RAG) over Enterprise Data
- Create grounded AI experiences by connecting LLM applications to Datasphere models and enterprise sources.
- Engineer retrieval strategies respecting domain boundaries, freshness, and access controls.
- Hybrid Modernization Migration (BW bridge patterns)
- Enable transition paths from legacy warehouse investments using Datasphere / BW bridge.
- Lakehouse style Layering Data Quality by Design
- Implement layered design patterns (e.g., Bronze/Silver/Gold) for data landing, cleansing, and model publishing.
- Embed quality controls, validation checks, and reproducible transformations.
- Agentic Orchestration Tooling
- Build data agents that can plan, call tools, retrieve context, and generate answers with citations.
- Implement prompt templates, tool schemas, and safe action boundaries.
- Evaluation, Observability Responsible AI
- Establish offline/online evaluation loops for conversational analytics and data agents.
- Add telemetry for AI interactions to improve reliability and cost efficiency.
- Integration Collaboration
- Partner with business, data governance, and platform teams.
- Drive reusable patterns and accelerators.
Requirements & Tech Stack
- Primary Skills (AI Native Must Have)
- SAP BTP Datasphere: data modeling, spaces, sharing patterns, enterprise semantic design.
- Strong data warehousing fundamentals.
- Hands-on building with LLMs + RAG: retrieval, grounding, prompt/tool design, evaluation.
- Solid software engineering fundamentals: testability, CI/CD mindset, reliable integrations.
- Secondary / Strongly Beneficial Skills
- Migration/modernization experience leveraging BW bridge style transition patterns.
- Layered architecture implementation (Bronze/Silver/Gold).
- Familiarity with vector search / embedding pipelines.
Qualifications
- 15 years full-time education.
Note: This role does not center on training foundation models from scratch. The emphasis is on building agentic apps and governed retrieval on enterprise data. This role owns AI behavior (grounding, evaluation, safety) end to end.