AI Agent Developer

We are seeking an experienced AI Agent Developer to design, build, deploy, and support production-grade AI agents across our enterprise technology ecosystem. This role is central to our AI initiative to deliver AI agents—that drive measurable business outcomes across retail, service, finance, and customer experience. The ideal candidate has hands-on experience shipping AI agents in enterprise environments and is comfortable working across multiple platforms including Anthropic Claude, Google Gemini on Vertex AI, Microsoft Azure AI, DevRev, and Sierra AI. You will partner closely with solution architects, infrastructure engineers, data teams, and business stakeholders to turn use cases into deployed, monitored, production-ready agents. Core Responsibilities Agent Design & Development • Design, develop, and iterate on AI agents using agentic frameworks across Claude (MCP, tool use, multi-turn orchestration), Gemini on Vertex AI (Agent Builder, extensions, grounding), Azure AI (Azure OpenAI Service, Semantic Kernel, Promptflow), DevRev, and Sierra AI. • Implement agent architectures including ReAct, plan-and-execute, multi-agent orchestration, and retrieval-augmented generation (RAG) patterns. • Build agents that integrate with enterprise systems such as Snowflake, Salesforce, ServiceNow, and internal APIs via function calling, tool use, and MCP server configurations. • Develop and maintain reusable agent components, prompt libraries, and evaluation harnesses. Deployment & Production Operations • Deploy agents into production environments on GCP, Azure, and hybrid infrastructure with full CI/CD pipelines (Harness). • Implement observability, tracing, and logging for agent workflows using Dynatrace and platform-native tooling. • Build guardrails, content filtering, and safety mechanisms to ensure responsible agent behavior in production. • Own agent lifecycle management: versioning, A/B testing, canary deployments, rollback procedures, and performance monitoring. Data & Integration • Design and implement grounding pipelines that connect agents to enterprise data sources including Snowflake data warehouses, SharePoint document libraries, and Salesforce CRM. • Build and optimize vector search, embedding pipelines, and knowledge retrieval systems (pgvector, Vertex AI Search, Azure AI Search). • Develop API integrations using Kong/Konnect API gateway and RESTful service patterns. Security & Compliance • Implement prompt injection defenses, input/output validation, and PII handling safeguards for all agents. • Work with security teams to ensure agents meet enterprise security standards including CyberArk credential management and Chainguard container security. • Conduct red-team testing and adversarial evaluation of agent behaviors prior to production release. Collaboration & Enablement • Partner with AI Solution Architects to translate business requirements into technical agent specifications. • Contribute to internal developer documentation, runbooks, and best-practice guides for agent development. • Participate in code reviews focused on AI-generated code quality and security. • Support cross-functional teams in evaluating new agent platforms and capabilities. Required Qualifications • 5+ years of software development experience with at least 2 years focused on AI/ML agent development in enterprise environments. • Demonstrated hands-on experience deploying and supporting AI agents in production, not just prototypes—candidates must be able to speak to real-world deployments, failure modes, and lessons learned. • Production experience with two or more of the following platforms: Anthropic Claude (API, MCP, tool use), Google Gemini / Vertex AI (Agent Builder, extensions, grounding), Microsoft Azure AI (Azure OpenAI, Semantic Kernel, Promptflow), DevRev AI agents, Sierra AI conversational agents. • Strong proficiency in Python and/or TypeScript/Node.js for agent development. • Experience with agentic design patterns: ReAct, chain-of-thought, multi-agent coordination, tool use / function calling, and RAG architectures. • Working knowledge of LLM fundamentals: tokenization, context windows, prompt engineering, fine-tuning, and evaluation methodologies. • Experience with CI/CD pipelines, containerized deployments (Docker, Kubernetes), and cloud-native infrastructure on GCP and/or Azure. • Familiarity with enterprise data platforms, particularly Snowflake, for agent grounding and retrieval. • Strong communication skills with the ability to explain complex AI concepts to non-technical stakeholders. Preferred Qualifications • Experience with Model Context Protocol (MCP) server development and integration. • Hands-on experience with Vertex AI Agent Builder and Google’s agent ecosystem. • Familiarity with agent evaluation frameworks and LLM benchmarking (e.g., LangSmith, Braintrust, custom eval harnesses). • Experience building consumer-facing conversational AI agents in retail or automotive verticals. • Knowledge of API gateway patterns (Kong/Konnect) and enterprise integration architectures. • Background in prompt injection defense, AI red-teaming, and responsible AI practices. • Experience with observability platforms such as Dynatrace for AI workload monitoring. • Contributions to open-source AI/agent projects or published work in the AI agent space Skills: machine learning,llm,artificial intelligence