About the job
Job Purpose
Responsible for designing, building, and operating production-grade AI agents, orchestration frameworks, and intelligent automation systems that power the organization's customer, operational, and enterprise capabilities. The incumbent works closely with engineers and cross-functional teams to ensure AI solutions are accurate, reliable, and performant -- forming the engineering foundation that scales the organization's AI capabilities from discrete initiatives into a cohesive, enterprise-grade platform.
Key Result Responsibilities
AI Agent Design & Engineering Design and build production-grade AI agents, multi-agent orchestration frameworks, and conversational systems.
Implement dialogue management, prompt engineering patterns, and context persistence architectures for scalable conversational experiences.
Intelligent Automation & Channel Delivery Deliver AI-powered automation across customer interaction channels including chat, WhatsApp, email, and voice.
Integrate AI agents with reservation, pricing, and operational backend systems to enable end-to-end workflow automation.
Knowledge Systems & Retrieval
Build and operate retrieval-augmented generation (RAG) mechanisms enabling AI agents to utilize enterprise knowledge effectively.
Key Result Responsibilities-Continued
Production Quality & Reliability Ensure AI solutions meet production standards for accuracy, latency, reliability, and safety.
Establish evaluation frameworks, testing environments, and model lifecycle practices for continuous improvement.
Collaboration & Engineering Excellence Work closely with engineers, business, and operations teams to translate requirements into scalable AI capabilities.
Mentor engineers, champion best practices, and contribute through design reviews and architectural documentation.
Coach and guide junior engineers in AI engineering practices and promote a culture of excellence and continuous improvement.
Qualifications
(Academic, training, languages) Bachelor's degree in Computer Science, Software Engineering, Artificial Intelligence, or a related field.
Strong proficiency in Python for building production-grade AI/ML systems.
Good understanding of agent workflows, tool usage, and execution patterns Familiarity with Model Context Protocol (MCP).
Strong understanding of prompt engineering and structured prompting techniques.
Ability to implement context persistence and memory strategies.
Familiarity with multi-channel delivery (chat, WhatsApp, email, voice).
Ability to integrate enterprise knowledge sources (documents, APIs, structured data).
Familiarity with guardrails, fallback strategies, and failure handling.
Awareness of AI safety practices (e.g., prompt injection, output validation, guardrails).
Strong experience in building REST APIs and microservices.
Understanding of asynchronous processing and event-driven architecture.
Familiarity with CI/CD pipelines and cloud environments.
Understanding of scalability, reliability, and cost optimization basics.
Understanding of monitoring, logging, and pe.
Understanding of evaluation approaches for AI systems (testing, benchmarking) Ability to optimize for latency, cost (token usage), and response quality.
Fluent in English Language.
Work Experience-Internal With 2+ years of hands-on experience building production GenAI systems.
Hands-on experience designing AI agents and multi-agent orchestration systems.
Experience
designing multi-turn conversational systems and dialogue flows.
Experience
with Human-in-the-Loop (HITL) workflows.
Experience
with vector databases and semantic search.
Hands-on experience building RAG pipelines.
Experience
integrating AI with enterprise backend systems.
Experience
with LLM APIs, SLMs, and agent frameworks.
Experience
with Docker and Kubernetes.
Experience
working with production-grade AI systems.
Work Experience With 2+ years of hands-on experience building production GenAI systems.
Hands-on experience designing AI agents and multi-agent orchestration systems.
Experience
designing multi-turn conversational systems and dialogue flows.
Experience
with Human-in-the-Loop (HITL) workflows.
Experience
with vector databases and semantic search.
Hands-on experience building RAG pipelines.
Experience
integrating AI with enterprise backend systems.
Experience
with LLM APIs, SLMs, and agent frameworks.
Experience
with Docker and Kubernetes.
Experience
working with production-grade AI systems.