Project brief
프로젝트 내용
Role: Generative AI Engineer / Architect - Indians only
Location: Remote
Experience: 9+ years
Role Summary
We are looking for a hands-on Generative AI Engineer/Architect with strong expertise in Microsoft Azure AI services, Azure AI Foundry (Microsoft Foundry), and Anthropic Claude models.
The candidate will be responsible for designing, developing, evaluating, and deploying secure, enterprise-grade Generative AI applications and AI agents. Strong practical experience with RAG, prompt engineering, agentic workflows, tool/function calling, Claude APIs, and responsible AI practices is required.
The ideal candidate should be able to translate business requirements into scalable GenAI architectures and take solutions from POC through production deployment.
Key Responsibilities
Design and implement enterprise GenAI solutions using Azure AI Foundry/Microsoft Foundry and Anthropic Claude.
Build intelligent assistants, copilots, knowledge-search applications, and autonomous/human-in-the-loop AI agents.
Develop agentic workflows using Claude tool use/function calling.
Integrate Claude models through supported APIs, SDKs, and enterprise model endpoints.
Design and implement RAG solutions using Azure AI Search, embeddings, vector search, reranking, and enterprise data sources.
Develop system prompts, reusable prompt templates, structured outputs, and multi-step prompt chains.
Evaluate and recommend models based on accuracy, reasoning, latency, context-window requirements, security, and cost.
Build model evaluation frameworks covering groundedness, relevance, coherence, hallucination, safety, tool-call accuracy, and task completion.
Implement AI guardrails, content filtering, prompt-injection protection, data privacy controls, and responsible AI practices.
Integrate GenAI applications with enterprise systems, APIs, databases, document repositories, and collaboration platforms.
Develop backend AI services and APIs using Python, FastAPI, REST APIs, Azure Functions, and/or Azure Container Apps.
Implement monitoring for token consumption, response quality, latency, errors, model usage, and operational costs.
Establish LLMOps/GenAIOps practices covering prompt versioning, automated evaluation, CI/CD, deployment, monitoring, and rollback.
Collaborate with business stakeholders, product teams, data engineers, security teams, and cloud architects.
Provide architectural guidance, conduct technical reviews, and mentor development teams.
Create solution architecture documents, technical designs, implementation plans, and reusable GenAI accelerators.