Software Senior Principal Engineer / Autonomous AI Software Engineering

Software Senior Principal Engineer – Autonomous AI Software Engineering
Software engineering is being reshaped by autonomous AI agents that can plan, write, test, and review code with increasing independence. Our team works at the forefront of that shift, bringing agent-driven autonomy into the software development lifecycle so that engineers set direction and make key decisions while agents handle execution.
Because the agent landscape evolves rapidly, we stay hands-on: exploring promising approaches, validating them through rigorous experimentation on real engineering workloads, and turning successful outcomes into enterprise-grade software development practices. We are a small, AI-native team operating with startup agility—emphasizing high autonomy, rapid iteration, and seamless human-AI collaboration.
Join us to do the best work of your career and make a profound impact as a Software Senior Principal Engineer on our AI Governance Engineering team in Hopkinton, Massachusetts. This is an onsite role.
What You'll Achieve
You will serve as the technical leader and architect for autonomous AI across our software development lifecycle. You will define the target architecture for agent-driven engineering, lead objective evaluations of commercial, open-source, and in-house technologies, and translate proof-of-concept results into actionable technical strategies for executive leadership.
This is a hands-on architecture role: you will write code, build critical prototypes and integrations directly, and guide engineering teams by technical example from pilot stages to enterprise-scale deployment.
You Will:
Define Reference Architectures: Architect autonomous agent systems within the SDLC, encompassing orchestration, multi-agent design patterns, tool use, Model Context Protocol (MCP), sandboxed runtime environments, model routing, human-in-the-loop controls, and integration with existing engineering platforms and governance frameworks
Lead Technical Evaluations: Maintain deep visibility into the agent ecosystem, establish objective evaluation criteria (capability, autonomy, quality, security, scalability, extensibility, and total cost of ownership), and design proof-of-concept tests to drive build-versus-buy decisions
Own Verification and Validation: Establish the testing, qualification, and acceptance standards for agent-generated code and artifacts, including continuous benchmarking and regression monitoring for agent platforms and underlying models
Architect for Trust and Safety: Design frameworks ensuring auditability, traceability of agent actions, reproducibility, data privacy, failure containment, robust permission models, and mitigations against vulnerabilities such as prompt injection and unauthorized tool execution
Drive Platform Adoption: Establish the autonomy maturity roadmap, directly construct core platform capabilities and integrations, mentor senior technical talent, and align technical initiatives across cross-functional engineering organizations
Technologies You'll Work With:
Agents & LLMs: Commercial and open-source autonomous coding agents/frameworks, frontier and open-weight models, LLM gateways, function/tool calling, Retrieval-Augmented Generation (RAG), and the Model Context Protocol (MCP)
Engineering & Integration: Python, TypeScript / Node.js, REST and GraphQL APIs, Git-based workflows, and modern CI/CD automation
Verification & Testing: Automated testing frameworks, Test-Driven Development (TDD), mutation and property-based testing, static code and security analysis, and LLM evaluation benchmarks
Runtime & Observability: Sandboxed container execution (Docker, Kubernetes), OpenTelemetry tracing, operational metrics/dashboards, and PostgreSQL
Essential Requirements:
12+ years of software engineering experience, including 5+ years as an architect or technical lead for large-scale distributed platforms
Proven track record architecting, deploying, and maintaining production-grade autonomous agent platforms (including agent runtimes, orchestration engines, tool/MCP integrations, context management, and dynamic model routing)
Demonstrated experience designing multi-agent architectures for autonomous software development (e.g., task decomposition, planner/executor/reviewer paradigms, structured agent handoffs, and human-in-the-loop validation delivering production pull requests)
Deep technical expertise in secure agent execution environments: sandboxing, workload scheduling, persistent state management, distributed tracing/replay, cost optimization, fine-grained access control, and defense-in-depth against prompt injection and sandbox escape
Direct experience building evaluation frameworks, automated benchmarking suites, and regression testing pipelines for agents, prompts, and model upgrades, backed by comprehensive knowledge of the open-source and commercial agent ecosystem
Desirable Requirements:
Bachelor’s degree in Computer Science, Engineering, or equivalent practical experience
Experience scaling an agent platform from prototype to widespread enterprise adoption, or prior experience building commercial agent-based software products
Advanced familiarity with long-horizon agent reasoning techniques, including autonomous planning, reflection, self-correction, and reinforcement learning from feedback
Recognized technical leadership in agentic AI, demonstrated through open-source contributions, technical publications, patents, or benchmark releases
About Dell Technologies — ISG Developer Experience
Dell's Infrastructure Solutions Group is a global leader in Solutions, Storage, Compute, and Networking. The Developer Experience organization within ISG is responsible for developer productivity, tooling, observability, and platform engineering for approximately 9,000 engineers. Our current mandate spans agentic SDLC transformation, AI tooling governance, and the operating model changes required to make AI-assisted development the norm — not the exception.
Infrastructure Solutions Group (ISG) builds the products that power infrastructure, solutions, and data management our customers need most. Our teams design and develop the hardware and software that connect infrastructure, accelerate computational workloads, integrate across the stack, protect data continuity, and deliver the platforms, applications, and di

Work arrangement
No