Description

Key Responsibilities

• Design and architect Agentic AI systems capable of autonomous reasoning, decision-making, and task execution.
• Build and implement multi-agent frameworks that collaborate to solve complex workflows.
• Define architecture for LLM-powered applications, including prompt orchestration, tool usage, and memory management.
• Integrate AI agents with enterprise systems, APIs, and data platforms.
• Lead the design of AI pipelines, orchestration layers, and evaluation frameworks.
• Establish best practices for AI governance, safety, observability, and monitoring.
• Collaborate with product managers, data scientists, and engineering teams to translate business requirements into AI-driven solutions.
• Guide teams in deploying scalable AI solutions on cloud platforms such as Azure, AWS, or GCP.
• Evaluate and adopt emerging technologies in autonomous AI, reasoning systems, and agent frameworks.
• Provide technical leadership and mentorship to AI/ML engineers.

Required Qualifications

• Bachelor’s or Master’s degree in Computer Science, Artificial Intelligence, Data Science, or related field.
• 8-9+ years of experience in software engineering, machine learning, or AI architecture.
• 3+ years of experience working with LLM-based systems and generative AI solutions.
• Strong experience designing Agentic AI or multi-agent architectures.
• Proficiency with Python and AI/ML frameworks.
• Hands-on experience with LLM orchestration frameworks such as LangChain, AutoGen, CrewAI, Semantic Kernel, or similar.
• Experience working with vector databases (Pinecone, Weaviate, FAISS, etc.).
• Knowledge of RAG architectures, prompt engineering, tool integration, and memory management in AI agents.
• Experience deploying AI workloads in cloud environments (Azure, AWS, or GCP).
• Strong understanding of API design, microservices architecture, and distributed systems

Key Skills

Education

Bachelor's or Master's degrees