Software Engineer I (ML/AI Platform)

About Tekion

Tekion is positively disrupting the automotive industry with the first and fastest cloud-native automotive platform. This platform includes the revolutionary Automotive Retail Cloud (ARC) for retailers, Automotive Enterprise Cloud (AEC) for manufacturers, and Automotive Partner Cloud (APC) for technology partners. Tekion connects the entire automotive retail ecosystem through one seamless platform, leveraging cutting-edge technology, big data, machine learning, and AI to bring together OEMs, retailers/dealers, and consumers. Tekion employs close to 3,000 people across North America, Asia, and Europe.

About the Role

This role is integral to powering Tekion’s AI-native, end-to-end automotive platform by transforming unified dealership data across DMS, CRM, Digital Retail, Service, and Payments into real-time intelligence. You will operationalize a graph-based contextual ecosystem to enable agents to retrieve relevant context, enforce policy, and personalize experiences that drive measurable dealer outcomes. Additionally, you will build the resilient control layer (MCP) and the LLM Gateway, facilitating safe, cost-efficient, and multi-provider LLM usage. A key responsibility will be to define standards for building, evaluating, deploying, and governing agentic systems, allowing product teams to ship AI features quickly, safely, and at scale. This role also involves building the platform for classical ML models that drive optimization across dealership operations.

This opportunity offers a direct, measurable impact on dealer outcomes and consumer experiences across Tekion’s Automotive Retail Cloud and Automotive Enterprise Cloud. You will have end-to-end ownership of an LLM control plane and gateway that serve multi-tenant workloads under strict SLAs, quality, and cost guardrails. Leveraging a rich vertical dataset and domain graph spanning sales, service, parts, F&I, accounting, and consumer touchpoints, you will power context-aware agents and retrieval-augmented generation. You will also shape core levers such as agent orchestration patterns, evaluation frameworks, and safety guardrails to translate improvements in latency, reliability, evaluation quality, and safety into key dealer KPIs like upsell, cycle time, CSAT, and service revenue. Furthermore, you will maintain and enhance the platform to support classical supervised and unsupervised ML models.

Responsibilities

• Build and run the LLM control plane/gateway, including smart routing, rate limits/quotas, failover, and token/cost tracking.
• Ship a unified API and SDKs (REST/gRPC) with normalized schemas, structured outputs, caching, and full observability (traces/logs/metrics).
• Enforce safety and privacy by default through content filtering, prompt/response validation, and PII redaction.
• Enable multi-model, multi-vendor use of LLMs with automated canarying and versioning.
• Own the agent runtime: tool registry, permissions, function calling, grounding, and retrieval.
• Design orchestration patterns (sequential, planner-executor, streaming) and manage agent state and long-running workflows.
• Enable platform components for training and scoring pipelines for classical ML (e.g., XGBoost/LightGBM/linear/trees) and deep models; standardize experiment tracking and packaging.
• Create components to monitor model and data drift, retraining and tuning models as needed to maintain accuracy and relevance.
• Add human-in-the-loop review and safe-actioning before agents interact with dealer systems.
• Evolve the domain graph and entity resolution; build reliable data ingestion pipelines.
• Serve real-time context to agents (profiles, inventory, pricing, appointments, service history) with access controls and lineage.
• Power retrieval with hybrid search (graph + vector + keyword) and smart cache/TTL to balance accuracy, latency, and cost.
• Run continuous offline/online evaluations for quality, factuality, bias, and safety for the platform sanity.
• Define SLOs for latency (p50/p95), uptime, and cost view capabilities; enable autoscaling and spend controls.
• Maintain a model/agent registry, versioning, approvals, audit trails, and reproducibility; support compliances where needed.
• Provide templates/CLIs, sandboxes, and docs to enable product teams to build and ship fast; mentor engineers and champion MLOps and AI safety best practices.

Requirements

• 2+ years building large-scale data/ML or platform systems.
• Strong software engineering fundamentals (Abstracted API design, concurrency, distributed systems).
• Production experience with Python plus one of Java/Scala/Go; microservices and API design.
• Proficiency in MLOps at scale: pipelines (Airflow/Kubeflow), tracking/registry (MLflow), CI/CD for models, A/B testing, shadow/canary, and online feature computation (Spark/Flink/Kafka).
• Experience with Cloud and containers: AWS (preferred), plus Docker/Kubernetes; performance, reliability, and cost engineering in multi-tenant SaaS.
• Practical ML knowledge (feature engineering, training, evaluation, drift detection); experience deploying models that power user-facing workflows.
• Built or operated an LLM gateway/control plane: provider adapters, routing/policies, caching, quota/rate-limit, cost and token accounting.
• Experience with agentic systems: tool use/function calling, orchestration frameworks, human-in-the-loop, safety/guardrails, and online evaluation/telemetry.
• Proficiency in Graph and retrieval: knowledge graphs (e.g., Neo4j/Neptune/TigerGraph), GraphQL, vector search (e.g., pgvector/Qdrant/Milvus), hybrid retrieval patterns.

Preferred Mindset

• Platform-as-product: Obsess over developer experience, paved roads, and clear SLAs.
• Systems thinker: Observability, fallback, and access control are core, not afterthoughts.
• Passionate about AI: Enjoys enabling real-world LLM and agentic use cases.
• Cost-aware builder: Treats latency and dollars as first-class metrics and designs for graceful degradation.
• Vendor-agnostic thinker: Chooses the right model/provider per use case; builds for portability and resilience.
• Documentation and teaching: Makes complex systems understandable and uplevels teams.