Enterprise Applied AI Solutions Engineer (Implementing Agentic & Generative AI features)

This is a delivery-focused role combining hands-on implementation with light product ownership and operational discipline. 1. Applied Solution Delivery & Iteration (65% of time) Build and enhance AI-powered features (e.g., copilots, summarization, classification, routing, Q&A) aligned to defined business workflows. Partner with business users to clarify requirements, run demos, capture feedback, and iterate toward measurable outcomes. Support pilot launches, troubleshoot issues, and contribute to smooth adoption through user training and clear documentation. 2. Knowledge-Based Agents & Conversational Design (25% of time) Develop agents grounded in the company's internal knowledge base, using Retrieval-Augmented Generation (RAG) patterns and retrieval quality improvements. Design conversational flows for internal functions (e.g., HR helpdesk), including intent handling, escalation paths, and handoff to human support when needed. Implement simple agentic or predictive models for operational use cases (e.g., predicting customer support ticket volume) under guidance from senior engineers. 3. Product Execution, Quality & Documentation (10% of time) Manage the feature backlog for an AI product area: write user stories, define acceptance criteria, and coordinate UAT. Contribute to evaluation and regression testing using approved checklists; help monitor quality, latency, and cost for deployed features. Create and maintain documentation (how-to guides, runbooks, and user enablement materials) to support long-term sustainability. 3+ years of experience in software engineering or applied solutions development (or equivalent practical experience). Proficiency in Python and API-based integration; working knowledge of SQL and data access patterns. Working familiarity with large language models (LLMs), prompt engineering, and Retrieval-Augmented Generation (RAG). Exposure to agent frameworks (e.g., LangChain, LlamaIndex, Semantic Kernel, or similar) and the ability to implement tool/function calling patterns. Basic understanding of enterprise security, privacy, and data governance requirements; ability to follow established guardrails and escalate risks early. Strong communication skills and the ability to collaborate effectively with technical and business stakeholders. Bachelor's degree in Computer Science, Engineering, or a related field (or equivalent practical experience). Ideal Candidate Profile: Who Thrives in This Role Builders Over Theorists: You enjoy shipping working software and iterating based on user feedback. User-Centered Mindset: You like sitting with users, mapping workflows, and improving day-to-day productivity. Pragmatic Technologist: You choose simple, reliable approaches and adopt new techniques when they clearly improve outcomes. Quality-Driven: You care about correctness, safety, and operational reliability, and you follow established production standards. Continuous Learner: You stay current on rapidly evolving GenAI capabilities and apply them responsibly. Generous Collaborator: You document clearly, communicate proactively, and work well across teams. What Success Looks Like First 6 Months: Deliver 1-2 AI features or agents to pilot or production with clear user feedback, basic evaluation coverage, and documentation. Demonstrate measurable value within the target workflow. First Year: Own a small AI product area end-to-end (backlog, iterations, releases). Ship multiple improvements that increase adoption and reduce manual effort while maintaining enterprise standards for security and quality. Ongoing Success: Deployed solutions sustain strong adoption within the target user base. Quality remains stable through regression testing and monitoring. Contributions improve delivery speed and reuse through well-documented patterns and assets.