Jobs · Engineering · South Carolina

AVP DevX - AI Engineer/Technical Lead

LPL Financial · Fort Mill, SC · 4 wk ago
Engineering$148k–$246k/yrFull-time

About the role

As AVP, Software Engineer, you will serve as a senior individual contributor and technical leader within the Developer Experience Platform and PDLC AI Enablement domain. This role focuses on two closely connected areas: Internal Developer Platform (IDP) — delivering self-service automation, golden paths, and reference architectures. AI and GenAI enablement — providing production-ready RAG pipelines, agents, plugins, and AI-assisted development tools as first-class platform capabilities.

Responsibilities

  • Design, build, and evolve cloud-native platform services and AI/GenAI capabilities that improve developer productivity and software delivery outcomes.
  • Architect and deliver enterprise-grade AI solutions, including RAG and GraphRAG pipelines, multi-agent systems, LLM-powered developer tools, plugins, MCP tools, and reusable skills.
  • Drive Claude Suite adoption end-to-end, including claude.ai, Claude API, Claude Code, system prompt design, and context window management.
  • Lead large-scale Cursor AI integration, including workspace rules, .cursorrules governance, MCP server connections, and AI-assisted development workflows.
  • Build and operate LLM evaluation pipelines using RAGAS, LangSmith, and custom evaluation harnesses; implement AI observability such as tracing, hallucination detection, latency and token cost dashboards, drift monitoring, and guardrails.
  • Contribute to the build-out of the Internal Developer Platform, including Backstage plugin development, golden-path templates, and self-service portals for application, infrastructure, and architecture automation.
  • Participate in Agile ceremonies including Scrum events and PI Planning; collaborate with Product, Architecture, Security, and Platform partners on delivery planning and technical design.
  • Facilitate solution design sessions, technical demos, Lunch & Learn events, office hours, and developer community forums to share knowledge and address engineering pain points.
  • Translate developer feedback and partner team needs into scalable platform and AI capabilities.
  • Develop and maintain technical documentation including design documents, runbooks, disaster recovery strategies, and release documentation in alignment with enterprise standards.
  • Develop and maintain web, API, and AI-enabled services, including secure coding practices, vulnerability remediation, testing, and CI/CD automation.
  • Partner closely with Architecture, Security, Cloud, DevSecOps, Quality Engineering, Compliance, and Release teams to define and promote reference architectures and best practices.
  • Embed DevSecOps and Responsible AI principles, including shift-left security, SAST/DAST integration, SBOM generation, software supply chain controls, and AI governance.
  • Track and improve platform adoption metrics, AI usage and quality indicators, and developer experience outcomes.
  • Present platform architecture, AI capabilities, and technical recommendations to senior leadership and executive stakeholders.

Requirements

  • 10+ years of hands-on, end-to-end application development experience across .NET, Angular, React, TypeScript, and Python in cloud-hosted (AWS), microservice-based environments.
  • 2–5+ years of hands-on experience delivering AI/ML and GenAI solutions in enterprise production environments.
  • 2+ years experience with the Claude Suite, including claude.ai, Claude API, Claude Code, system prompt design, and context window management.
  • 2+ years Architect-level experience with RAG and GraphRAG pipelines, including chunking strategies, embedding models, and vector stores such as Pinecone, pgvector, or Azure AI Search.
  • 2+ years experience designing and implementing AI agents, including multi-agent orchestration, tool use, memory strategies, and agent communication protocols.
  • API design expertise, including OpenAPI, GraphQL, versioning strategies, rate limiting, and gateway integration.
  • Experience with GitOps, blue-green and dark release deployment strategies, and Infrastructure as Code.
  • Track record of contributing to and scaling Internal Developer Platforms, including paved paths, golden paths, and self-service portals.
  • DevSecOps and InnerSource practices, including contribution models, discoverability, reuse, and security automation.
  • Commitment to automated testing, code quality, and continuous improvement using industry-standard tools and frameworks.
  • Clear written and verbal communication, with the ability to explain complex platform and AI concepts to technical and non-technical audiences.
  • Ability to influence cross-functional teams and senior stakeholders through technical expertise and collaboration rather than formal authority.

Core Competencies

  • Designing complete cloud solutions with consideration for scalability, security, data protection, disaster recovery, FinOps (including AI workload cost), and compliance.
  • Experience with graph databases such as Neo4j or Amazon Neptune.
  • Experience with OpenTelemetry custom instrumentation.
  • Familiarity with advanced prompt engineering patterns (e.g., React, SELF-RAG) and model fine-tuning approaches.
  • Experience working within Responsible AI and AI governance frameworks.
  • Demonstrated curiosity, adaptability, ownership mindset, and comfort working in fast-changing technical environments.
  • Experience with LLM orchestration frameworks such as LangChain, LangGraph, Semantic Kernel, or AutoGen.

Preferences

  • Master’s degree in Computer Science or a related field.
  • AWS certifications (Developer, Solutions Architect, or equivalent).
  • Experience with graph databases such as Neo4j or Amazon Neptune.
  • Experience with OpenTelemetry custom instrumentation.
  • Familiarity with advanced prompt engineering patterns (e.g., React, SELF-RAG) and model fine-tuning approaches.
  • Experience working within Responsible AI and AI governance frameworks.
  • Demonstrated curiosity, adaptability, ownership mindset, and comfort working in fast-changing technical environments.
  • Experience with LLM orchestration frameworks such as LangChain, LangGraph, Semantic Kernel, or AutoGen.

Pay Range

$147,500.00 - $245,900.00

Similar jobs