Sr 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 looking for a Senior Software Engineer who applies the principles of secure software engineering to the design, development, maintenance, testing, and evaluation of software and cloud infrastructure that supports this initiative.
As a senior member of the engineering organization, you will be expected to contribute beyond feature implementation by influencing development practices, mentoring teammates, raising engineering standards, and helping guide technical decision-making across products and services. You'll regularly balance short-term delivery objectives with long-term maintainability, scalability, and operational excellence.
This is early-stage work with executive sponsorship, direct access to AWS technical teams, and the autonomy to shape how the platform is built.
What You'll Do
Platform Integration & Connector Governance

• Own the enterprise connector catalog - define integration standards, security review gates, and onboarding playbooks for teams publishing MCP servers to Quick.
• Build platform-level integration infrastructure: auth plumbing (Entra/OAuth 2.0), connector health monitoring, and lifecycle tooling.
• Serve as the senior technical contact for domain teams (Snowflake, Salesforce, ServiceNow, Seismic) building MCP servers - unblock them, enforce guardrails, review designs, and ensure production readiness.
• Build connectors for systems where no dedicated team exists - AS400 wholesale auction databases, multi-step Databricks pipelines, internal REST/gRPC services, or whatever the business needs next.

AI Platform Engineering & Product Development

• Own and evolve the AI Artifact Hub - harden the product, improve reliability, and ship features that make it a core part of how the org builds with AI.
• Build and improve knowledge ingestion pipelines - chunking strategies, metadata extraction, and retrieval quality tuning.
• Develop agents, skills, and automation workflows that solve real business problems through the Quick platform.
• Design and implement fine-grained access controls and DLP enforcement - when an agent queries Snowflake or Office 365 on behalf of a user, it must strictly respect row-level permissions and never surface unauthorized data in prompt contexts.
• Adopt spec-driven, verification-first development practices - define expected behavior before implementation, especially when building with AI-assisted tooling.

Reliability, Observability & Evaluation

• Build the operational backbone for AI at scale - cost tracking by team/department, proactive circuit breakers for runaway token loops, and fallback handling when underlying services degrade.
• Design evaluation frameworks and automated "ground truth" test suites - measure whether changes to agent instructions improve or degrade accuracy across dozens of business workflows before they hit production.
• Build feedback loop APIs (Lambda, Step Functions) that capture human-in-the-loop corrections and feed quality signals back into the platform.
• Implement observability across the stack: usage metrics, latency, error rates, cost dashboards, and security-aware alerting.

Collaboration & Growth

• Participate in design and code reviews. Mentor junior engineers through pairing and knowledge sharing.
• Collaborate with the Principal Engineer on architecture decisions and technical direction.
• Work directly with AWS technical teams to troubleshoot issues, provide feedback, and adopt new capabilities.

Who You Are

• Bachelor's degree (list any requirements of discipline here) and 4 years' experience in a related field. The right candidate could also have a different combination, such as a master's degree and 2 years' experience; a Ph.D. and up to 1 year of experience; or 16years' experience in a related field.
• 5+ years of professional software development experience, including designing, building, and operating production systems.
• Strong proficiency in Python, including building APIs, data pipelines, and integrations.
• Hands-on experience with AWS services (Lambda, S3, IAM, API Gateway, CloudWatch, Step Functions, or similar).
• Experience building integrations with third-party APIs and SaaS platforms, including authentication flows (OAuth 2.0, OIDC).
• Experience with Infrastructure as Code (Terraform preferred) and CI/CD pipelines (GitHub Actions preferred).
• Solid understanding of distributed systems concepts: fault tolerance, idempotency, eventual consistency, and graceful degradation.
• Experience designing and enforcing authorization policies in multi-tenant or multi-user systems (row-level security, ABAC, or similar).
• Comfort working in a small, fast-moving team where you own what you build end-to-end.
• Strong communication skills. Able to explain technical decisions clearly and collaborate across teams.
• 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 for production platform systems.

Preferred Qualifications

• Experience with AI/ML-powered systems, with exposure to emerging patterns such as RAG, knowledge retrieval, or agent-based architectures.
• Experience with Amazon Bedrock, AWS managed AI/ML services, or a comparable enterprise AI platform.
• Familiarity with the Model Context Protocol (MCP) or experience building agent/tool integration layers.
• Experience with Snowflake, semantic views, or similar data platform technologies.
• Background in knowledge graphs, embeddings, vector stores, or enterprise search/retrieval systems.
• Experience building evaluation or testing frameworks for non-deterministic systems (ML model eval, A/B testing infrastructure, or similar).
• Familiarity with cost optimization in cloud-native architectures - FinOps thinking, usage metering, or chargeback systems.
• Experience with data loss prevention, PII detection/redaction, or security controls in data pipelines.
• Experience with event-driven architectures or workflow engines (Step Functions, Temporal).
• Experience building or operating internal developer platforms or developer tooling.
• Experience taking ownership of an inherited codebase and improving it to a well-documented, supportable state.
• Prior work in automotive, media, or another large enterprise with a complex system landscape is an advantage but not required.

USD 101,500.00 - 169,100.00 per year
Compensation:
Compensation includes a base salary in the range of $101,500.00 - $169,100.00. 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