Sr. AI Engineer

Overview

Role Summary

We are seeking an experienced AI professional to design, develop, and deploy enterprise-grade Agentic AI solutions powered by LLMs. The ideal candidate will have strong expertise in prompt engineering, agent orchestration frameworks, multi-agent architectures, memory and state management, RAG systems, and production deployment on cloud platforms.

Key Responsibilities

• Design and build LLM-powered agentic systems capable of planning, reasoning, tool usage, and multi-step workflow execution.
• Develop orchestration pipelines using LangGraph, LangChain, or Semantic Kernel.
• Implement agentic patterns including Planner-Executor, ReAct, Supervisor-Worker, and Multi-Agent Collaboration.
• Create and maintain reusable Agentic Skills, tool integrations, memory systems, checkpoints, and task-tracking mechanisms.
• Lead prompt engineering efforts including system prompts, tool/function calling, structured outputs, guardrails, and instruction tuning.
• Integrate APIs, enterprise services, search systems, and external tools into agent workflows.
• Implement automated testing, evaluation frameworks, observability, tracing, monitoring, and cost optimization.
• Ensure enterprise-grade security through prompt injection protection, RBAC, sandboxing, audit logging, and input/output validation.
• Translate business requirements into technical designs, HLDs, LLDs, and scalable AI architectures.
• Drive innovation by researching and implementing emerging Agentic AI techniques and best practices.

Required Skills

• Strong hands-on experience with Prompt Engineering and Agentic AI development.
• Expertise in LangGraph, LangChain, Semantic Kernel, or similar orchestration frameworks.
• Experience with context engineering, memory management, state management, checkpoints, scratchpads, and task orchestration.
• Proficiency in Python (preferred) or TypeScript/JavaScript.
• Experience with RAG, hybrid retrieval, reranking, chunking, and vector databases (Pinecone, FAISS, Azure AI Search, etc.).
• Knowledge of GitHub, DevOps, CI/CD, enterprise code management, and cloud platforms (Azure, AWS, or GCP).
• Experience building user-facing AI applications (chatbots, voice assistants, workflow automation).
• Strong analytical, problem-solving, communication, and stakeholder management skills.

Preferred

• Experience with OpenAI Agent Skills, Claude Skills, or similar agent skill frameworks.
• Experience with LLM evaluation frameworks, agent testing methodologies, and production-scale AI deployments.
• Understanding of secure tool execution, cloud computing technologies, and modern AI trends.