Design the blueprints for our AI ecosystem—selecting models, designing RAG (Retrieval-Augmented Generation) pipelines, and ensuring our AI initiatives are scalable and ethical
Job Summary
Design the blueprints for our AI ecosystem—selecting models, designing RAG (Retrieval-Augmented Generation) pipelines, and ensuring our AI initiatives are scalable and ethical.
Architect end-to-end GenAI solutions, including model selection, vector database orchestration, and API integration, while designing high-performance inference pipelines and determining deployment strategies.
Implement "AI Guardrails" to manage hallucination, data leakage, and prompt injection risks, and optimize token usage and compute costs.
Matching Summary
Design the blueprints for our AI ecosystem—selecting models, designing RAG (Retrieval-Augmented Generation) pipelines, and ensuring our AI initiatives are scalable and ethical.
Skills & Requirements
Must-have
Generative AI ecosystem design
Retrieval-Augmented Generation (RAG) pipelines
LLM, SLM, Multi-modal model selection
Vector database orchestration
High-performance inference pipelines
Python development with FastAPI/Flask
Nice-to-have
Scalable and ethical AI initiatives
AI Guardrails implementation
Cost optimization for token usage
Agile methodologies and DevOps practices
Flexible working arrangements
Key Requirements
3+ years as Solution Architect with AI/ML exposure
Expertise in LangChain and VertexAI
Hands-on experience with Gemini, Anthropic (Claude), Open Source models
Proficiency with Graph & Vector DBs
Experience with AWS Bedrock and Google Vertex AI
Experience with Docker and Kubernetes
Bachelor's or Master's degree in CS, Engineering, AI or related field