Hybrid AI Infrastructure Engineer

Posted 3 weeks ago

Apply now

About the role

  • Design and implement scalable backend architectures for AI workloads (inference, orchestration, monitoring).
  • Own distributed job orchestration with Temporal and related systems.
  • Improve data pipeline performance by designing smarter caching strategies (e.g., file deduplication, hot/cold storage, Redis caching layers) to reduce redundant compute and API calls.
  • Build observability, monitoring, retries, and fault tolerance into all workflows.
  • Manage infrastructure reliability, incident response, and performance.
  • Develop tooling and platform infrastructure to support rapid growth.
  • Partner with ML engineers to bring models to production at scale.

Requirements

  • 4+ years of backend engineering (Python is a must).
  • Strong background in distributed systems, job orchestration, and task queues.
  • Deep knowledge of concurrency, parallelism, and multithreading—including async/await, event loops, thread pools, synchronization primitives, deadlocks, and race conditions—is a must.
  • Hands-on experience with Temporal, Redis, Airflow, Celery, RabbitMQ (or similar).
  • Experience with LLM serving and routing fundamentals (rate limiting, streaming, load balancing, budgets).
  • Comfortable with containers & orchestration: Docker, Kubernetes.
  • Familiarity with cloud platforms (AWS/GCP) and IaC (Terraform).
  • Experience with multiple storage systems: S3, Postgres, MongoDB, Redis, and Elasticsearch.
  • Track record scaling systems in startups or fast-paced environments.
  • Understanding of deploying, monitoring, and optimizing AI/ML systems in production with strong CI/CD practices.

Benefits

  • Offers Equity

Job title

AI Infrastructure Engineer

Job type

Experience level

Mid levelSenior

Salary

$150,000 - $220,000 per year

Degree requirement

Bachelor's Degree

Location requirements

Report this job

See something inaccurate? Let us know and we'll update the listing.

Report job