> Markdown version of [/jobs/ext/3673664-software-principal-engineer-autonomous-ai-software-engineering](https://www.wearedevelopers.com/jobs/ext/3673664-software-principal-engineer-autonomous-ai-software-engineering). Every page supports `.md` or `Accept: text/markdown`. Links point to the HTML versions so they work for humans too. Agent guide: [/agents.md](https://www.wearedevelopers.com/agents.md).

---

# Software Principal Engineer / Autonomous AI Software Engineering

- **Company:** Dell Technologies Inc.
- **Location:** Hopkinton, MA, United States
- **Experience:** Expert
- **Salary:** $172,000.0 - $236,500.0
- **Contract:** Internship / Graduate position
- **Skills:** Application Programming Interfaces (APIs), Artificial Intelligence, Automation of Tests, Code Review, Continuous Integration, Issue Tracking Systems, Python (Programming Language), PostgreSQL, Node.Js, Open Source Technology, Software Engineering, Verification and Validation (Software), Systems Integration, TypeScript, Test-Driven Development (TDD), Large Language Models, Multi-Agent Systems, Prompt Engineering, Agentic-AI, Git Flow, Information Technology, Graphql, Drift Detection, Evaluation of Large Language Models, Restful APIs, Model Context Protocol, Software Version Control, Docker
- **Published:** October 10, 2026
- **Apply:** https://www.jobmonkeyjobs.com/career/28097841/Software-Principal-Engineer-Autonomous-Ai-Software-Engineering-Massachusetts-Hopkinton-1312

## About the Role

* 8+ years of software engineering experience;. Ability to thrive in an AI-native, startup-style team where ambiguity is normal and execution speed matters
 * Proven track record of building core components of an autonomous agent platform in production (e.g., agent execution loops, planning and task decomposition, tool-calling/MCP layers, or memory and context management). Building simple LLM API wrappers or using commercial coding assistants alone is not sufficient
 * Experience operating long-running autonomous agents in production: isolated sandbox environments (containers or microVMs), state checkpointing/resume, failure recovery, loop and drift detection, and token/cost budgets
 * Deep expertise in context engineering for software agents on large, complex codebases: code indexing and retrieval, repository maps, and context compaction, with measurable improvements in task success rates
 * Experience with evaluation-driven agent development: designing benchmarks and evaluation suites to measure task completion, iterating on agent behavior based on metrics, and enforcing automated verification

Desirable Requirements:

 * Bachelor's degree in Computer Science, Engineering, or equivalent experience
 * Experience deploying, extending, or integrating commercial or open-source autonomous agent platforms in an enterprise environment (including custom agents, SDK/MCP extensions, and self-hosted/private deployments)
 * Production experience with multi-agent systems (planner, executor, and reviewer patterns; agent handoffs), durable execution engines, published agent benchmarks, or contributions to open-source agent frameworks

## Description

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 more execution.

Because the agent landscape evolves rapidly, we stay hands-on: exploring the most promising approaches, proving them with rigorous experiments on real engineering work, and turning successful patterns into standard development practices. We are a small, AI-native team operating like a startup-prioritizing high autonomy, rapid experimentation, and daily human-AI collaboration.

Join us to do the best work of your career and make a profound impact as a Software Principal Engineer on our AI Governance Engineering team in Hopkinton, Massachusetts. This is an onsite role.

What You'll Achieve

You will be the hands-on engineer who turns autonomous agents from impressive demos into dependable engineering practice. You will set up and run proofs of concept of agent platforms and approaches against real codebases and tasks, measure objectively what they can and cannot do, and integrate viable solutions into our development lifecycle-operating within the architecture and evaluation framework defined by our architect.

You will spend most of your time building and experimenting (70%+), using AI agents as a core part of your daily workflow., * Run hands-on proofs of concept and pilots of autonomous software-engineering agents and agent platforms, from environment setup and integration through results, on representative real-world engineering work

 * Build evaluation harnesses: realistic task suites, benchmarks, and metrics for output quality, level of autonomy, reliability, speed, cost, and security, enabling fair and repeatable comparisons
 * Verify and validate agent output using automated tests, mutation testing, static and security analysis, acceptance-criteria checks, and calibrated human review to identify failure points
 * Integrate agents into the engineering toolchain (source control, CI/CD, issue tracking, specifications, and quality gates) via APIs, MCP, and custom tools, building extensions where standard solutions fall short
 * Increase autonomy safely by implementing guardrails, sandboxing, observability (traces and replay), and feedback loops, helping engineering teams adopt agent-driven workflows with confidence

Technologies You'll Work With:

 * Agents and LLMs: Commercial and open-source autonomous coding agents, agent frameworks, frontier and open-weight models, LLM gateways, tool calling, retrieval-augmented generation (RAG), and the Model Context Protocol (MCP)
 * Engineering: Python, TypeScript / Node.js, REST and GraphQL APIs, Git-based workflows, and CI/CD pipelines
 * Verification and Validation: Automated test frameworks, test-driven development (TDD), mutation and property-based testing, static and security analysis, and LLM evaluation frameworks
 * Runtime and Observability: Docker and Kubernetes for sandboxed agent execution, OpenTelemetry tracing, metrics, dashboards, and PostgreSQL