Description
Design and implement backend services for Generative AI applications, including APIs, orchestration layers, integrations, and data processing pipelines.
Build RAG-based solutions using document ingestion, text extraction, chunking, embeddings, vector databases, hybrid search, reranking, and LLM-based response generation.
Develop agentic AI solutions, including tool-using agents, multi-agent workflows, task orchestration, memory, planning, and integration with enterprise systems.
Implement AI assistants and copilots that connect to internal APIs, databases, document repositories, SharePoint, storage systems, knowledge bases, and enterprise applications.
Use frameworks such as LangChain, LlamaIndex, Semantic Kernel, AutoGen, CrewAI, or similar to build GenAI workflows and agentic applications.
Work with enterprise GenAI platforms such as Microsoft Copilot Studio, Amazon Bedrock, and Azure AI Foundry.
Evaluate GenAI applications for answer quality, retrieval quality, hallucination reduction, latency, cost, scalability, and maintainability.
Collaborate with architects, product owners, business stakeholders, and data teams to translate requirements into technical AI solutions.
Contribute to reusable components, reference architectures, implementation standards, and best practices for GenAI delivery.
Ensure solutions follow good practices regarding security, access control, data privacy, observability, testing, and maintainability.