Staff Machine Learning Engineer, Platform (MLOPS)
Credit Acceptance6 days ago
Southfield, MI, USA +2 moreStaff+
Base Salary
$185k - $259k/yr
Responsibilities
- Own end-to-end deployment paths for ML and GenAI training and inference pipelines, model registries, serving endpoints, versioning, and controlled promotion across environments.
- Operate production model runtime health through monitoring, alerting, drift and quality-regression detection, latency and throughput objectives, autoscaling, incident response, and corrective actions.
- Route production agents through governed AI and MCP gateways, migrate existing agents, and maintain scoped, versioned, least-privilege tool surfaces.
- Build production agent evaluation, online scoring, behavioral monitoring, sampling and judge pipelines, and release gates that prevent regressions.
- Build and maintain observability and evaluation infrastructure, including multi-turn and multi-step traces, telemetry capture, logging standards, pipeline plumbing, and data contracts.
- Measure platform unit economics, including cost per inference, document, and interaction, to inform build-versus-buy and hosting decisions.
- Create reusable pipeline templates, deployment patterns, reference implementations, and internal tooling for product teams.
- Partner with Cloud Engineering, Data Engineering, Security, and SRE on enterprise governance, identity, and observability.
- Respond to AI-specific production incidents involving prompt injection, rogue-agent cost spikes, data-classification exposure, agent delegation abuse, and model endpoint failures.
- Maintain ML platform architecture documentation and system diagrams, mentor engineers and interns, and raise standards through design and code review.
Requirements
- Bachelor’s degree in Computer Science, Engineering, Statistics, or a relevant technical field and at least 7 years of relevant experience, or a relevant master’s degree and at least 5 years of relevant experience.
- At least 5 years of experience building and operating production ML or AI systems, with ownership of at least two major platform areas such as training or inference pipelines, model serving, model registries, or production monitoring.
- Experience owning a production ML or AI service through deployment, monitoring, incident diagnosis, and remediation.
- Strong Python and SQL skills with production engineering practices including version control, testing, code review, and CI/CD for ML workloads.
- Production experience with a cloud ML platform; AWS and Databricks are strongly preferred, including model serving, orchestration, and MLflow or a similar registry or experiment-tracking system.
- Understanding of the operational differences between LLM/GenAI workloads and traditional ML, including token costs, latency, caching, batching, and nondeterministic output.
- Experience operating LLM or agent applications behind gateway or proxy layers, including routing, fallback, credential management, rate limiting, and budget enforcement.
- Working knowledge of agent tool-calling architecture and the Model Context Protocol, including MCP server operation, tool authorization, and gateway-brokered access.
- Experience with containerization and infrastructure as code.
- Preferred experience includes GPU-backed model serving, OpenTelemetry, Dynatrace, model-serving optimization, Databricks Unity Catalog, regulated financial-services AI systems, agentic applications, managed agent or tool gateways, MCP servers, and agent interoperability and identity standards.
- Ability to communicate technical trade-offs clearly, resolve incidents effectively, teach others, prioritize under pressure, and build relationships across the organization.
- Must reside in or be willing to relocate to the greater Southfield, Michigan area; greater Bellevue, Washington area; or San Francisco Bay Area, California.
Benefits
- Competitive benefits package including 401(k) match, adoption assistance, parental leave, tuition reimbursement, and comprehensive medical, dental, and vision coverage.
- Additional nonstandard benefits and an inclusive, culturally diverse workplace.
- Hybrid work model with two work-from-home days and three standard in-office days each week at the local office.
Categories
About Credit Acceptance
Credit Acceptance is a public auto finance company that partners with a nationwide network of car dealers to provide indirect vehicle loans to consumers, including those with limited or challenged credit. The company purchases and services retail installment contracts and shares collections with dealers through structured programs. Founded in 1972 and headquartered in Southfield, Michigan, it trades on NASDAQ as CACC and operates across the U.S.