Staff Inference Engineer - Bellevue Hybrid

Vašingtonas Hibridinis Visas etatas Vadovas Privaloma Kalba: anglų Inžinierius

Debesija Kubernetes Paskirstytosios sistemos

Aprašymas

Build and operate production model-serving and inference systems for high-throughput, low-latency AI workloads
Optimize inference infrastructure for token throughput, latency, scalability, and cost efficiency across diverse models and workloads
Design systems that use GPUs efficiently while delivering consistent performance and reliability
Advance inference-platform scalability and operational maturity as customer demand increases
Work with AI training, GPU performance, orchestration, and infrastructure teams to move models from development into production
Establish monitoring, alerting, and operational practices that support dependable inference services
Diagnose and resolve performance, reliability, and capacity issues across inference workloads
Shape architecture decisions and engineering standards as the platform develops

Reikalavimai

Experience building and operating production machine learning inference or model-serving systems at scale
Strong understanding of latency, throughput, memory utilization, and cost-efficiency trade-offs involved in serving large AI models
Experience designing reliable distributed systems or production infrastructure
Understanding of GPU-backed AI workloads and the challenges of scaling inference systems
Strong engineering fundamentals and the ability to independently own complex technical problems
Comfort working in a fast-moving environment where systems and processes are built from the ground up
Experience with modern inference-serving frameworks such as vLLM, SGLang, TensorRT-LLM, Triton Inference Server, or comparable technologies
Experience optimizing LLM inference workloads or large-scale AI serving platforms
Background operating API-based AI products or high-volume production services
Experience with GPU scheduling, distributed systems, Kubernetes, or cloud infrastructure platforms
Familiarity with quantization, batching, caching, or performance tuning
Experience at a hyperscaler, AI lab, GPU cloud provider, or large-scale ML infrastructure organization
U.S. work authorization is required
Visa sponsorship is not currently available
Willingness to work in a hybrid arrangement in downtown Bellevue, Washington, with at least three days per week in the office once the permanent office is established

Privalumai

Competitive base pay for the Bellevue market
Merit-based increases
Annual bonus
Long-term incentives
Medical insurance
Dental insurance
Vision insurance
401(k) plan
Company 401(k) match
Paid holidays
Startup ownership and meaningful technical impact
Collaboration with an experienced AI infrastructure team

Susiję darbai

11 – 50 Darbuotojai

Kelionės Konsultavimas Logistika

Vokietija Hibridinis Visas etatas Vyresnysis specialistas Privaloma Kalba: vokiečių Privaloma Kalba: anglų Duomenų inžinierius

AWS Azure Debesija Google Cloud Platform Java Linux Maven Mikropaslaugos NoSQL Python Spring SQL Unix

Build cloud, data, and analytics solutions for ADEAL Systems, taking technical ownership of architecture, data pipelines, and customer projects.

Atidaryti

Nuotolinis Sutartis Vidutinis lygis Vyresnysis specialistas Privaloma Kalba: anglų Duomenų inžinierius

65 $ – 75 $ / valanda

Manage enterprise data initiatives, report migrations, and user adoption for TEKsystems. Track project milestones, risks, dependencies, and stakeholder communications in a remote role.

Atidaryti

Nuotolinis Sutartis Vidutinis lygis Vyresnysis specialistas Privaloma Kalba: anglų Duomenų inžinierius

65 $ – 75 $ / valanda

Coordinate enterprise data initiatives, report migrations, and user adoption for TEKsystems technology services clients. Support governance, project tracking, and delivery across business and technical teams.

Atidaryti

51 – 200 Darbuotojai

SaaS Sveikatos draudimas Sveikatos priežiūra

Izraelis Hibridinis Visas etatas Vidutinis lygis Vyresnysis specialistas Privaloma Kalba: anglų Duomenų inžinierius

AWS Debesija ETL Postgres Python SQL

Build AWS data pipelines and platform infrastructure for Nym’s healthcare coding engine. Strengthen delivery, observability, reliability, and security for systems handling patient data.

Atidaryti

51 – 200 Darbuotojai

Konsultavimas Logistika Sveikatos priežiūra

Vašingtonas Nuotolinis Visas etatas Vadovas Privaloma Kalba: anglų Mašininio mokymosi inžinierius

AWS Debesija Python Terraform

Lead LLM, agentic AI, and machine learning proofs of concept for Amgen’s biotech medicines business. Turn validated solutions into enterprise-ready applications.

Atidaryti

51 – 200 Darbuotojai

Kvalifikuoto darbuotojo vizos rėmėjas Konsultavimas Logistika Sveikatos priežiūra

Brazilija Nuotolinis Visas etatas Vidutinis lygis Vyresnysis specialistas Privaloma Kalba: anglų Dirbtinio intelekto inžinierius Mašininio mokymosi inžinierius

AWS Azure Debesija Docker Google Cloud Platform Kubernetes Python React SQL Terraform

Build production-grade generative AI and agent workflows for Ambush’s financial services clients. Develop Python and FastAPI services, SQL data workflows, retrieval-augmented generation, and cloud-based AI systems.

Atidaryti

201 – 500 Darbuotojai

Elektroninė prekyba Fintech SaaS

Vokietija Nuotolinis Visas etatas Vidutinis lygis Vyresnysis specialistas Privaloma Kalba: vokiečių Privaloma Kalba: anglų Mašininio mokymosi inžinierius

AWS Azure Django Docker Kubernetes Python Ruby Ruby on Rails Terraform

Build backend infrastructure and AI-enabled learning products for GFN, a German education provider. Develop scalable educational platforms with a focus on robust software architecture and practical machine learning.

Atidaryti

51 – 200 Darbuotojai

Debesų saugumas SaaS Saugumas

Izraelis Hibridinis Visas etatas Vidutinis lygis Vyresnysis specialistas Privaloma Kalba: anglų Dirbtinio intelekto inžinierius Mašininio mokymosi inžinierius

AWS Azure Debesija Google Cloud Platform Kibernetinis saugumas Kubernetes Python

Develop and deploy LLM agents for Upwind Security’s cloud security platform. Research, evaluate, and build autonomous workflows for investigating and remediating runtime threats.

Atidaryti

Nuotolinis Sutartis Vidutinis lygis Vyresnysis specialistas Privaloma Kalba: anglų Duomenų mokslininkas

65 $ – 75 $ / valanda

Coordinate enterprise data initiatives, report migrations, and adoption of new processes and reporting solutions for TEKsystems. Track project progress, risks, deliverables, and communications with business and technical stakeholders.

Atidaryti