Description

Define end-to-end architecture for agentic AI solutions, including multi-agent systems, orchestration layers, and enterprise integrations.

This role is on-site.

Responsibilities

• Design and implement scalable agent frameworks using LangChain, Semantic Kernel, AutoGen, or CrewAI.
• Lead development of LLM-driven systems (Azure OpenAI, OpenAI, Anthropic) with robust prompting strategies.
• Architect RAG pipelines, memory systems, and tool integration layers.
• Establish best practices for AI governance, security, and Responsible AI.
• Provide technical leadership and mentorship to development teams while collaborating with business stakeholders.

Required Skills

• 10+ years of experience in software engineering, AI/ML, or solution architecture.
• Strong expertise in Python and modern backend architectures.
• Hands-on experience with LLM ecosystems and agent frameworks.
• Proven experience designing multi-agent systems and distributed architectures.
• Deep understanding of prompt engineering, LLM optimization, embeddings, and vector databases (FAISS, Pinecone, Azure AI Search).
• Experience with Retrieval-Augmented Generation (RAG).
• Strong knowledge of API design, microservices, and event-driven architecture.
• Familiarity with security, authentication (OAuth, SSO), and data governance.
• Experience with cloud platforms (Azure preferred, AWS/GCP acceptable).

Preferred Skills

• Experience with Model Context Protocol (ClientP) or similar integration standards.
• Knowledge of MLOps / LLMOps frameworks.
• Certifications (Azure AI Engineer, Solutions Architect, etc.).

Key Skills

Education

Bachelor's degree