Generative AI Engineer

Get AI-powered advice on this job and more exclusive features.Direct message the job poster from Orion InnovationWe are seeking an experienced and forward-thinking AI Lead Engineer to join our AI Ops delivery team. In this role, you will lead the design, development, and delivery of GenAI-powered agentic systems that automate complex business processes across domains such as HR, Payroll, SAP, and Client Delivery. This role combines deep hands-on engineering with architectural ownership and close collaboration with product managers and domain experts.ResponsibilitiesOwn the technical design and architecture of GenAI agent workflows within the Business PodServe as a hands-on developer, actively contributing to the design, coding, and delivery of production-grade agents and toolsLead code and design reviews, ensuring alignment with architectural standards and platform best practicesCollaborate with the AI Ops Core Pod to adopt and influence reusable assets, frameworks, and integration patternsDesign and implement LLM-powered agent workflows using frameworks such as LangChain, LangGraph, or CrewAIDevelop prompt chains, agent tools, and custom modules that support reasoning, summarization, and multi-step task executionIntegrate agents with enterprise systems (e.g., Workday, SAP, Salesforce) via REST APIs, SDKs, or message queuesBuild and manage agent lifecycle components, including initialization, memory/state handling, and fallback logicImplement and consume vector store integrations, prompt templates, and retrieval-augmented generation (RAG) techniquesEnsure workflows are robust, secure, and observable, with proper logging, monitoring, and exception handlingPartner with Product Managers, SMEs, and QA to translate business processes into agentic workflows and iterate based on feedbackContribute to the automation of testing, deployment, and validation pipelines for AI agentsMaintain thorough documentation of agent behavior, design decisions, and integration logic for operational readiness and knowledge transferQualificationsBachelor’s or Master’s degree in Computer Science, Software Engineering, or a related technical field4+ years of experience in developing and deploying production-grade AI/ML or automation solutionsStrong proficiency in Python, with hands-on experience using FastAPI, REST APIs, and background task orchestrationDeep familiarity with agentic frameworks such as LangChain, LangGraph, CrewAI, ReAct, or similarUnderstanding of LLM orchestration, including prompt design, tool usage, context management, and agent memoryExperience integrating with enterprise systems via APIs, event/message queues (e.g., Kafka, Service Bus), and webhooksSolid foundation in distributed system design, including state management, retries, error handling, and resilienceExperience with business process automation or workflow automation in real-world environmentsComfortable working with SQL/NoSQL databases, including data modeling and validationKnowledge of containerization (Docker), orchestration platforms (Kubernetes), and deployment to cloud platforms (Azure, AWS, or GCP)Understanding of security concepts including authentication (OAuth2), authorization, and secure API integrationExposure to multi-agent patterns (e.g., supervisor-worker, planner-executor, judge-critic) is a strong plusNice to HaveContributions to open-source agent frameworks or AI tooling.Experience working with observability and monitoring tools to track agent performance.Exposure to knowledge graphs, memory management systems, or retrieval-augmented generation (RAG) pipelines.Seniority levelMid-Senior levelEmployment typeFull-timeJob functionIT Services and IT Consulting #J-18808-Ljbffr