Skip to main content
TALENT247 // SPECIALIST AI EXECUTIVE SEARCH & TECHNICAL RECRUITMENT
OPS · MLOps & Platform

Senior MLOps Platform Engineer, Model & Feature Serving

Seattle, WA · Full-time · Hybrid

AI Specialism

MLOps & Platform

Workplace

Hybrid

Location

Seattle, WA

Compensation

$195k – $275k

annual package

Role Dossier & Specification

REF: SENIOR-MLOPS-PLATF

THE CLIENT & MANDATE

Our client is a globally scaled enterprise data and AI platform company powering mission-critical analytics, vector retrieval, and compound AI systems for thousands of Fortune 2000 organizations. Their Seattle AI Platform group owns the control plane and ultra-low-latency serving infrastructure behind custom language models, embedding endpoints, and real-time online feature stores.

They have retained Talent247 to appoint a Senior MLOps Platform Engineer for Model & Feature Serving in Seattle, WA. The successful candidate will build high-reliability multi-tenant control planes, zero-downtime canary routers, and sub-10ms online feature/vector lookup services supporting millions of requests per second across global cloud regions.

KEY RESPONSIBILITIES

  • Architect and scale multi-tenant model-serving and online feature-serving data planes delivering <10ms p99 lookup latencies and 99.99% availability across AWS, GCP, and Azure.
  • Build intelligent gateway routing layers supporting token-aware load balancing, prefix-cache affinity, shadow traffic mirroring, and automated canary rollbacks for LLM and classical ML endpoints.
  • Engineer unified governance, lineage, and RBAC enforcement pipelines connecting training checkpoints, quantized model artifacts, vector indices, and live inference telemetry.
  • Design fast autoscaling controllers and warm-pool GPU/CPU provisioning engines that react to bursty enterprise agent workloads within seconds.
  • Implement streaming inference-log capture and drift-monitoring sinks feeding offline evaluation and continuous fine-tuning loops without impacting serving tail latency.
  • Drive operational excellence through chaos testing, multi-region failover automation, and crisp SLO instrumentation.

TECHNICAL ENVIRONMENT & OFFERING

Stack: Go, Rust, Scala/Java, Python, Envoy, gRPC, Kubernetes, RocksDB/serverless key-value stores, Prometheus/OpenTelemetry, AWS/GCP/Azure. Workplace: Hybrid in Seattle, WA. Compensation: $195,000 – $275,000 base salary plus high-value equity grants, annual bonus/refreshers, and comprehensive US health & 401(k) benefits.

Core Requirements

ESSENTIAL QUALIFICATIONS

  • 5+ years of distributed systems, MLOps platform, or cloud infrastructure engineering experience operating high-QPS multi-tenant services.
  • Production mastery of Go, Rust, C++, or Scala/Java alongside strong Kubernetes controller/operator and Envoy/gRPC networking expertise.
  • Proven track record building model-serving platforms, online feature stores, real-time vector indices, or API gateways under strict sub-10ms to sub-50ms p99 SLAs.
  • Deep familiarity with multi-cloud IAM/security isolation, zero-downtime deployment patterns, and distributed state consensus.
  • Strong operational ownership across observability, capacity modeling, and root-cause performance debugging.

PREFERRED / BONUS EXPERIENCE

  • Experience orchestrating LLM serving runtimes (vLLM, TensorRT-LLM, SGLang, Triton Inference Server) and KV-cache-aware request routing.
  • Background working on storage-backed low-latency serving engines (RocksDB, Redis, Aerospike, Apache Arrow Flight).
  • Open-source contributions to Kubernetes, Envoy, Ray Serve, MLflow, or cloud-native CNCF projects.

Position Telemetry

Location Seattle, WA (Hybrid)
Department MLOps & Platform
Employment type Full-time
Workplace type Hybrid
Headcount 2 openings
Salary range
$195k – $275k annual package