Role & responsibilities
Conduct stakeholder discovery and translate business goals into AI use cases,

requirements, and acceptance criteria.
Define data requirements: sources, access, quality, governance and retention.
Design GenAI/ML approaches (RAG, fine-tuning, agent workflows) with clear

assumptions and tradeoffs.
Create evaluation criteria and validation plans (offline tests, human review, regression).
Break down AI RFP/RFI requirements into scope, risks, dependencies, and level-of-

effort estimates.
Write proposal-ready technical narratives: architecture, methodology, implementation

plan, and MLOps/LLMOps.
Build rapid demos/POCs to validate feasibility (retrieval, tool/function calling,

integrations).
Develop and orchestrate agents in Microsoft Copilot Studio (connectors, actions,

governance).
Implement and deploy solutions on AWS/Azure; leverage SageMaker and cloud-native





services for scalable inference.
Collaborate with SMEs and delivery teams to create reusable assets (templates,

prompts/modules) and smooth handoffs. Skills (Required + Valuable to have)
Robust Python development; experience building APIs/services (e.g., FastAPI/Flask)

and integrating enterprise systems.
GenAI systems: RAG pipelines, prompt/tool routing, grounding/guardrails, and evaluation frameworks.
Cloud: AWS (S3, IAM, CloudWatch) with SageMaker for training/inference and deployment patterns.
Valuable to have: Azure ecosystem familiarity (data/AI services) and hybrid cloud architectures.
Good to have: ETL concepts and tools; familiarity with AWS Glue and data pipeline patterns.

📌 Ai Engineer Chennai (India)
🏢 Straive
📍 India