Inference Platform Engineer Jobs

1 job found

Today

Sr AI Engineer (Emerging AI)

DAT Seattle, WA

Seattle, WA

Today

$162k - $207k/yr Full time Backend Developer Artificial Intelligence Data Platform

Apply Now

Job Description

DAT is seeking a Senior AI Engineer (Emerging AI) to build and take ownership of the platform behind DAT’s agentic solutions. The role emphasizes scalable AI infrastructure on AWS, reliable model delivery, and production-grade evaluation, monitoring, and governance for freight and logistics use cases.

Responsibilities

Design, build, and operate shared services that enable engineers and business users to ship models, including a model gateway for LLM access, inference endpoints for real-time and batch scoring, feature storage, vector search, and a common SDK.
Lead architecture for large-scale AI systems by producing design documents and driving cross-functional alignment across Product and Engineering and Business stakeholders on how models are built and delivered.
Architect and operate scalable, reliable AI infrastructure on AWS using services including Bedrock, SageMaker, EKS, Redpanda, MSK (Kafka), Lambda, and S3, with infrastructure-as-code defined in Pulumi.
Develop offline and online evaluation systems to validate model and prompt changes, including regression suites, LLM-as-judge pipelines, A/B and shadow testing, and drift detection.
Own inference cost and latency as primary metrics, right-sizing GPU and serverless capacity, tuning batching, caching, and quantization, and providing teams visibility into workload costs.
Implement AI guardrails and operational controls, including prompt and output logging, PII handling, access controls, and model and dataset lineage to meet security and customer data commitments.
Drive adoption of modern software development practices across AI work, including automated testing, code reviews, CI/CD pipelines, and infrastructure-as-code.
Mentor engineers and data scientists on production ML and distributed systems, raising operational maturity across teams that build on the platform.
Lead response and resolution for complex production incidents involving AI services, conduct root cause analysis, and implement preventative measures.

Requirements

10+ years of software engineering experience, including substantial senior or staff-level time owning production infrastructure that other engineering teams depend on.
4+ years building and operating machine learning or AI platforms, taking models from notebook to production traffic and maintaining reliability.
Strong development language skills, ideally TypeScript/js, Java, or Go, with the engineering discipline to build libraries other teams adopt.
Extensive AWS experience with production systems, ideally including EKS/Kubernetes, Lambda, Redpanda, MSK/Kafka, S3, and Secrets Manager, plus infrastructure-as-code with Pulumi, Terraform, or similar.
Hands-on experience serving models at scale, including containerized inference, GPU scheduling, autoscaling, batching, and tradeoffs across real-time, streaming, and batch scoring.
Production experience with LLM systems, including retrieval-augmented generation, vector databases, prompt and context management, tool-calling or agent frameworks, and managed model APIs such as Amazon Bedrock.
Experience building evaluation and monitoring for models, including offline eval sets, online metrics, drift and data quality checks, and clear regression definitions.
Background in event-driven and distributed systems using Redpanda, AWS MSK, or Kafka.
Fluency with observability and on-call operations, including dashboards, APM traces, logs, alerts, SLOs, and using these tools to reduce incident frequency and MTTR.
Experience setting and raising engineering standards, such as PR and testing guidelines, deployment validation checklists, model release criteria, and post-incident review practices.
Technical leadership demonstrated through cross-team design work in ambiguous environments, clear system design documentation and operational runbooks, and alignment across Engineering, Product, and Operations.
Proven mentoring experience helping engineers and data scientists grow in system design, observability, and operational excellence.
Excellent communication skills to explain tradeoffs and system behavior to engineers, product managers, and non-technical stakeholders.

Technology Stack

TypeScript/js, Java, Go
AWS: Bedrock, SageMaker, EKS, Redpanda, MSK, Kafka, Lambda, S3, Secrets Manager
Pulumi, Terraform
LLM access, vector search, retrieval-augmented generation, vector databases
Tool-calling, agent frameworks
LLM-as-judge pipelines, A/B testing, shadow testing
Observability, APM traces

Location and Compensation

Location: Seattle, WA (hybrid)
Salary: USD 162,000 - 207,000 per year

Benefits

Medical, Dental, Vision, Life, and AD&D insurance
Parental Leave
Flexible Vacation Time (FVT)
Additional 10 holidays of paid time off per calendar year
401k matching (immediately vested)
Employee Stock Purchase Plan
Short- and Long-term disability sick leave
Flexible Spending Accounts
Health Savings Accounts
Employee Assistance Program
Additional programs including Employee Referral, Internal Recognition, and Wellness
Free TriMet transit pass (Beaverton Office)
Competitive salary and benefits package
Collaborative and supportive team culture
Work on impactful projects in a cutting-edge environment
Opportunity to make a real difference in the trucking industry
Employee Resource Groups

Bonus Skills

Experience with model fine-tuning, distillation, or parameter-efficient training, including when those approaches beat prompting.
Background in marketplace, pricing, forecasting, or document extraction problems.
Freight, logistics, or supply chain domain experience.

Application Deadline

Deadline: 11/30/2026

Why DAT

DAT is an award-winning employer of choice.
Hybrid work environment.
Values include integrity, mutual respect, open communication, and executing with excellence.
Employer of choice in the Portland metropolitan area for four decades.
Within one year of opening the Denver office, DAT was #26 on Built In Colorado’s 100 Best Places to Work in Colorado.

Washington Pay Transparency (WA Candidates)

DAT considers factors such as scope and responsibilities of the position, candidate work experience, education and training, core skills, internal equity, and market and business elements when extending an offer.

View full job page →

Get Inference Platform Engineer Jobs alerts

New Inference Platform Engineer Jobs, daily.