Principal Software Engineer

Cox Automotive is deploying enterprise AI capabilities on AWS Quick across the enterprise, helping teams work more effectively in their day-to-day operations.
We are seeking a Principal Software Engineer to own technical direction for the platform, the applications, and integrations around it. This role shapes architecture across two products: AWS Quick, an emerging AI platform for agents and enterprise connectors; and an established internal AI Artifact Hub used across Cox Automotive that lets engineering and product teams publish and share interactive artifacts through a web experience and an MCP server interface.
This is a hands-on technical leadership role. You will make the key architecture and engineering decisions, lead engineers through implementation, and stay close enough to the code to review designs, debug difficult issues, and contribute where it matters. The team builds connectors, agents, knowledge bases and data pipelines, and quality systems that integrate Quick with Cox Automotive's core enterprise tools and operational systems.
This is early-stage work with executive sponsorship, direct access to AWS technical teams, and the autonomy to define the architecture.
What You'll Do
Architecture & Technical Direction

• Own the end-to-end architecture for the AWS Quick customization layer, including connectors, agent orchestration, knowledge ingestion, service boundaries, and infrastructure as code.
• Define the Model Context Protocol (MCP) strategy for enterprise integrations: tool contracts, governance, authentication, authorization, and safety boundaries.
• Own the technical direction of the AI Artifact Hub. Assess its current state, define a hardening plan, and improve reliability as adoption grows.
• Make and document major architecture decisions, including the trade-offs behind them. Build for near-term delivery without closing off the platform's next stage.
• Work with Enterprise Architecture, Security, Cloud Automation, and AWS technical teams to align platform direction and resolve cross-team issues.

AI Platform Engineering & Quality

• Own the quality and evaluation approach for AI capabilities, including automated regression tests, measurable acceptance criteria, and human-in-the-loop (HITL) feedback.
• Lead technical decisions around enterprise knowledge and retrieval, including ingestion, content curation, metadata, knowledge graphs, retrieval quality, context management, and platform-supported RAG configuration.
• Define standards and reusable patterns for agents and skills.
• Set the design for MCP servers, tool interfaces, and structured APIs intended for agent use.
• Establish spec-driven, verification-first practices for AI-assisted software development. Evaluate new capabilities and adopt them when they improve delivery without weakening quality or security.

Resilient Distributed Systems

• Set production reliability standards for AI-enabled integrations, including monitoring, observability, graceful degradation, and incident response.
• Define failure and recovery patterns: timeouts, bounded retries with backoff, circuit breakers, and clear fallback behavior.
• Define idempotency and durable workflow patterns for operations that cross service or third-party boundaries.
• Lead response to significant platform incidents and drive the follow-up engineering work.

Technical Leadership & Influence

• Lead architecture and design reviews. Pair with engineers on the hardest problems and raise the team's engineering judgment.
• Guide the team's Python implementation through design, code review, debugging, and targeted production contributions.
• Serve as a senior technical contact for AWS on platform architecture, product capabilities, and roadmap needs.
• Explain technical direction and trade-offs clearly to engineering, product, security, and senior leadership.
• Represent the platform team in cross-organization technical forums and build alignment across team boundaries.

Who You Are

• Bachelor's degree in Computer Science and 10 years' experience in a related field. The right candidate could also have a different combination, such as a master's degree and 8 years' experience; a Ph.D. and 5 years' experience in a related field; or 22 years' experience in a related field.
• 10+ years of experience across the software development life cycle, architecture, and platform delivery.
• Strong experience designing and delivering cloud-native platforms on AWS, including compute, storage, networking, IAM, observability, and infrastructure automation.
• Experience designing, building, or operating AI/ML-powered systems, with exposure to emerging patterns such as RAG, knowledge retrieval, or agent-based architectures.
• Strong software engineering fundamentals and working proficiency in Python. Able to design, review, debug, and contribute to Python-based connectors, pipelines, and tooling.
• Experience defining evaluation and quality approaches for software, including regression testing, measurable acceptance criteria, HITL review, or other methods suited to non-deterministic systems.
• A track record of enterprise integration work across SaaS, data platforms, and operational systems, including API design, authentication (OAuth 2.0, OIDC, SSO), data quality, and reliability concerns.
• Demonstrated ownership of a platform or system architecture used by multiple engineering teams.
• Experience setting technical direction and influencing decisions across team boundaries without relying on formal authority.
• Experience establishing engineering practices and team norms in a newly formed team.
• Applicants must be authorized to work in the United States for any employer without current or future sponsorship.
• Ability to work in the office three days per week.
• Willingness to participate in an on-call rotation and lead incident response for production platform systems.

Preferred Qualifications

• Experience with Amazon Bedrock, AWS managed AI/ML services, or a comparable enterprise AI platform.
• Experience working directly with a cloud or platform vendor on product capabilities and roadmap priorities.
• Familiarity with the MCP specification and SDKs, or experience building comparable agent/tool integration layers and governance patterns.
• Background in knowledge graphs, graph databases, or enterprise knowledge and retrieval systems.
• Experience with Infrastructure as Code (preferably Terraform) and CI/CD for cloud or AI-enabled systems. Familiarity with GitHub Actions and self-hosted runners is a plus.
• Experience with HITL workflows, agent orchestration, evaluation harnesses, or LLM-backed middleware.
• Experience with Snowflake, including semantic views or similar semantic-layer technology.
• Background in data loss prevention, PII redaction, or zero-trust data pipelines.
• Experience building internal developer platforms, developer tooling, or platform-as-a-product capabilities.
• Experience taking ownership of an inherited codebase and bringing it to a supportable, well-documented state.
• Experience with event-driven architectures and workflow engines such as AWS Step Functions or Temporal.
• Experience establishing spec-driven development, evaluation, governance, or verification practices for AI-assisted engineering.
• Prior work in automotive, media, or another large enterprise with a complex system landscape is an advantage but not required.
• Experience designing and operating APIs for other teams, including versioning and backward compatibility.

USD 163,400.00 - 272,300.00
Compensation:
Compensation includes a base salary in the range of $163,400.00 - $272,300.00. The base salary may vary within the anticipated base pay range based on factors such as the ultimate location of the position and the selected candidate's knowledge, skills, and abilities. Position may be eligible for additional compensation that may include an incentive program.
Benefits:
The Company offers eligible employees the flexibility to take as much vacation with pay as they deem consistent with their duties, the company's needs, and its obligations; seven paid holidays throughout the calendar year; and up to 160 hours of paid wellness annually for their own wellness or that of family members. Employees are also eligible for additional paid time off in the form of bereavement leave, time off to vote, jury duty leave, volunteer time off, military leave, and parental leave.
EOE, including disability/vets