This role pays more than
81%
of similar roles. Most pay
$177,250–$254,750
— the shaded band above.
At the midpoint, this role pays about
$276k
versus about
$216k
for comparable roles.
Based on 240 similar postings.
Employer
About Dell Technologies
Dell Technologies is a US-based technology company that designs and sells PCs, servers, storage and networking hardware, along with related software and IT services. Its product lines include the XPS, Latitude and Alienware PCs and the PowerEdge server and PowerStore storage families.
Dell Technologies currently has
73 open roles
on FindRole.
Listed pay typically runs
$164,025–$225,750
across 64 roles with salary data.
As an Agentic Context Engineering Architect & AI Practitioner on the AI Development & Agent Ops team, you will design, build, and operate the enterprise AI Harness to enable secure, scalable, and governable AI-assisted software development. You will develop context engineering frameworks, manage knowledge ingestion and retrieval architectures, and implement agent memory systems including short-term and persistent patterns. Your daily work involves building shared services, developer tooling, and platform integrations while collaborating with security and infrastructure teams to ensure compliance. You will optimize context window efficiency, token utilization, and relevance scoring while establishing standards for metadata and information quality. The role requires expertise in LLMs, RAG architectures, vector databases, and agent orchestration. You will solve complex problems regarding how agents acquire and utilize information throughout the software development lifecycle to improve consistency and task completion accuracy.
Define standards and best practices for knowledge structures and content organization to maximize agent performance and trustworthiness.
Lead engineering excellence initiatives including observability, evaluation frameworks, and performance measurement across the AI ecosystem.
What we're looking for
12+ years in software engineering, platform engineering, distributed systems, or related technical leadership roles.
Hands-on experience with AI-assisted development, LLMs, agentic systems, RAG architectures, vector databases, and enterprise AI platforms.
Deep understanding of context engineering concepts including construction, retrieval strategies, composition, lifecycle management, and prompt orchestration.
Experience building platforms or services for knowledge retrieval, agent memory, context assembly, or AI workflow orchestration at scale.
Strong understanding of AI system architecture including embeddings, vector search, retrieval pipelines, and tool integration patterns.
Demonstrated ability to define architectures and deliver practical solutions from ambiguous problems while collaborating with cross-functional stakeholders.
Strong written and verbal communication skills to translate complex AI concepts into actionable technical guidance.
Experience with agentic development tools (e.g., GitHub Copilot, Claude Code), MCP, knowledge graphs, or enterprise governance (preferred).
Agentic AI
Large Language Models
Retrieval-Augmented Generation (RAG)
Machine Learning
Natural Language Processing
Distributed Systems
RLHF
RLAIF
Chain-of-Thought
Multi-agent Systems
Observability
Agentic AI
Large Language Models
Retrieval-Augmented Generation (RAG)
Machine Learning
Natural Language Processing
Reasoning Systems
RLHF
RLAIF
Distributed Systems
Chain-of-Thought
Multi-agent Systems
Orchestration Frameworks
Evaluation Frameworks
Observability
Agentic AI
Large Language Models
Retrieval-Augmented Generation (RAG)
Machine Learning
Natural Language Processing
Reasoning Systems
RLHF
RLAIF
Distributed Systems
Chain-of-Thought
Multi-agent Systems
Orchestration Frameworks
Evaluation Frameworks
Observability
Agentic AI
Large Language Models
Retrieval-Augmented Generation (RAG)
Reasoning Systems
Machine Learning
Natural Language Processing
RLHF
RLAIF
Distributed Systems
Multi-agent Systems
Orchestration Frameworks
Chain-of-Thought
Model Alignment
Evaluation Frameworks
Observability