Job description

Role : Principal Engineer Location : Charlotte NC (Onsite) Rate : $70 Indent : SF_OP_205828-11 / SF_OP_205828-14 Role Overview As a Principal Engineer for AI Tools, you will sit at the critical intersection of applied artificial intelligence, developer experience (DevEx), and high-scale distributed systems. You will define the technical strategy and reference architecture for internal AI tools—including autonomous agent hosting, AI-driven code review systems, internal vector/knowledge retrieval bases, and LLM orchestration gateways. This is a senior individual contributor (IC) leadership role focused on multiplying engineering efficiency, establishing security and evaluation best practices, and shaping how hundreds or thousands of engineers build software using AI-native workflows. Key Responsibilities Platform Architecture & Tooling Strategy • Design internal AI platforms : Architect scalable, low-latency internal developer tools, IDE extensions, cloud agent hosting infrastructures, and automated code review pipelines. • Set technical standards : Define reusable architectural patterns, governance-by-design frameworks, and SDK abstractions for secure LLM consumption across product and engineering teams. • Drive build vs. buy decisions : Evaluate emerging foundational models, inference engines, vector databases, and developer productivity ecosystems to optimize cost, latency, and quality tradeoffs. LLM & Intelligent Systems Integration • Orchestrate AI workflows : Integrate large language models (LLMs), retrieval-augmented generation (RAG), and agentic planning loops into developer and operational tooling. • Optimize retrieval & context : Build high-performance knowledge retrieval platforms that allow AI tools to safely query internal codebases, documentation, and system telemetry. • Implement guardrails & evaluation : Deploy rigorous evaluation frameworks to measure tool accuracy, catch behavioral drift, minimize hallucinations, and guard against data leakage or prompt injection. Technical Leadership & Mentorship • Multiply team capability : Mentor senior and staff engineers, raise the standard of engineering craftsmanship, and lead through technical influence rather than authority. • Partner across organizations : Collaborate closely with product management, security, infrastructure, and developer productivity teams to align tool roadmaps with company-wide goals. • Champion AI-native engineering : Evangelize best practices for AI-assisted development, prompt workflows, and generative AI operations (GenAIOps) across the company. Required Qualifications & Competencies Experience & Background • 10+ years of professional software engineering experience, with at least 5 years operating in a senior, lead, or principal capacity building large-scale backend platforms or developer tooling. • Demonstrated track record of architecting and shipping complex distributed systems or AI-integrated platforms into production environments. Technical Hard Skills • Proficiency in core languages : Expert-level programming skills in Python, Go, Rust, or C++. • AI & LLM Ecosystem : Deep command of LLM orchestration frameworks (e.g., LangChain, LlamaIndex), vector databases (e.g., Pinecone, Milvus, Qdrant), and RAG architecture design. • Cloud & Infrastructure : Strong command of containerization and orchestration tooling (Docker, Kubernetes) and modern cloud environments (AWS, GCP, or Azure). • Systems Design : Exceptional distributed systems design skills, focusing on high availability, low latency, multi-tenancy, and high-throughput data processing. Core Competencies • Agentic AI workflows and tool invocation patterns • Semantic search and hybrid retrieval systems • Observability, monitoring, and tracing (e.g., OpenTelemetry, MLflow) • AI security alignment, guardrails, and compliance Preferred Qualifications • Experience building internal developer platforms (IDPs) or developer productivity tools at scale. • Hands-on exposure to fine-tuning smaller open-source models (Llama, Mistral) for specialized domain tasks. • Contributions to open-source developer ecosystems or AI frameworks

Requirements

Must-haves

Role : Principal Engineer
Location : Charlotte NC (Onsite)
Indent : SF_OP_205828-11 / SF_OP_205828-14
Platform Architecture & Tooling Strategy
Design internal AI platforms : Architect scalable, low-latency internal developer tools, IDE extensions, cloud agent hosting infrastructures, and automated code review pipelines.
Set technical standards : Define reusable architectural patterns, governance-by-design frameworks, and SDK abstractions for secure LLM consumption across product and engineering teams.
Drive build vs. buy decisions : Evaluate emerging foundational models, inference engines, vector databases, and developer productivity ecosystems to optimize cost, latency, and quality tradeoffs.
LLM & Intelligent Systems Integration
Orchestrate AI workflows : Integrate large language models (LLMs), retrieval-augmented generation (RAG), and agentic planning loops into developer and operational tooling.
Optimize retrieval & context : Build high-performance knowledge retrieval platforms that allow AI tools to safely query internal codebases, documentation, and system telemetry.
Implement guardrails & evaluation : Deploy rigorous evaluation frameworks to measure tool accuracy, catch behavioral drift, minimize hallucinations, and guard against data leakage or prompt injection.
Technical Leadership & Mentorship
Multiply team capability : Mentor senior and staff engineers, raise the standard of engineering craftsmanship, and lead through technical influence rather than authority.
Partner across organizations : Collaborate closely with product management, security, infrastructure, and developer productivity teams to align tool roadmaps with company-wide goals.
Champion AI-native engineering : Evangelize best practices for AI-assisted development, prompt workflows, and generative AI operations (GenAIOps) across the company.
Required Qualifications & Competencies
Experience & Background
10+ years of professional software engineering experience, with at least 5 years operating in a senior, lead, or principal capacity building large-scale backend platforms or developer tooling.
Demonstrated track record of architecting and shipping complex distributed systems or AI-integrated platforms into production environments.
Technical Hard Skills
Proficiency in core languages : Expert-level programming skills in Python, Go, Rust, or C++.

Nice-to-haves

Experience building internal developer platforms (IDPs) or developer productivity tools at scale.
Hands-on exposure to fine-tuning smaller open-source models (Llama, Mistral) for specialized domain tasks.
Contributions to open-source developer ecosystems or AI frameworks

Application prep

Use the role’s language and application details while tailoring your materials.

Keywords to mirror

aillmpythongorustdockerkubernetesawsgcpazure

Platform: jobdiva
Effort: medium