AI Engineer

The primary objective of this role is to design, build, and maintain production-grade Agentic AI systems that can reason, interact with tools, retrieve relevant contextual knowledge, and execute complex, multi-step workflows securely and reliably. You will integrate LLMs, Mixture-of-Experts (MoE) models, embedding models, and vision models with enterprise systems, develop scalable AI orchestration frameworks, establish strong governance and observability practices, and continuously improve AI performance, efficiency, reliability, and security across the organization. Key Responsibilities Design, develop, and maintain Agentic AI systems that connect LLMs with tools, APIs, databases, and enterprise workflows to enable intelligent automation and action-oriented AI execution. Build and optimize AI agents capable of multi-step reasoning, tool utilization, and end-to-end workflow execution across various business processes. Develop and maintain scalable agent orchestration frameworks using technologies such as LangGraph, LangChain, PydanticAI, MCP, OpenClaw, OpenCode, or equivalent solutions. Design and optimize RAG pipelines, embedding strategies, prompt architectures, and contextual retrieval mechanisms to improve AI response quality, accuracy, and execution reliability. Evaluate and implement LLMs, MoE models, embedding models, and vision models according to specific enterprise use cases and requirements. Develop backend services, APIs, and system integrations using Python, Node.js, and JavaScript, enabling AI agents to securely interact with internal systems, databases, and workflow platforms. Automate AI-driven workflows using n8n or similar orchestration platforms, incorporating robust retry, fallback, error-handling, and exception-management mechanisms. Deploy and operate AI agents in production environments using Docker/Podman, CI/CD pipelines, and production-grade model serving infrastructure. Implement monitoring, logging, observability, and auditability mechanisms to track model and workflow performance and ensure secure, reliable, and compliant AI operations. Partner closely with Data, Platform, DevOps, and Business teams to translate business requirements into scalable, production-ready Agentic AI solutions. Maintain comprehensive technical documentation covering system architecture, prompts, tool integrations, deployment processes, and operational procedures. Ideal Candidate Profile Strong communication, collaboration, and technical documentation skills, with professional fluency in English. Bachelor's degree in Computer Science, Artificial Intelligence, Data Science, or a related discipline. At least 3 years of hands-on experience in AI/ML engineering, AI application development, or workflow automation. Strong proficiency in Python, Node.js, and JavaScript, with proven experience developing backend services, APIs, and production-grade integrations. Hands-on experience with LLMs, RAG, prompt engineering, and AI agent orchestration frameworks. Proven experience building Agentic AI workflows that connect AI models with tools, APIs, databases, and enterprise applications. Practical experience with LangGraph, LangChain, PydanticAI, MCP, vLLM, OpenClaw, OpenCode, or comparable technologies. Familiarity with LLMs, MoE models, embedding models, and vision models, particularly for enterprise AI applications. Experience with n8n or similar workflow automation and orchestration platforms. Experience deploying AI applications into production using containerization, CI/CD, and production serving environments. Understanding of model inference monitoring, model lifecycle management, AI evaluation, observability, and governance. Exposure to Big Data technologies such as Apache NiFi, Hortonworks/Cloudera, or Apache Ranger. Familiarity with data lakehouse architectures and distributed data ecosystems supporting analytics and AI workloads. Experience working with vector databases and enterprise-grade retrieval systems. Familiarity with OpenWebUI, LibreChat, or similar enterprise conversational AI platforms. Experience with on-premise/private AI infrastructure, observability platforms, and API gateways. Show less