Technical Lead Manager, ML Infrastructure (AI)

TL;DR

Technical Lead Manager, ML Infrastructure (AI): Leading the development and scaling of core infrastructure powering machine learning and self-hosted LLM applications with an accent on low-latency serving, streaming feature ingestion, and distributed training. Focus on building high-throughput GPU inference systems and improving developer ergonomics for ML scientists.

Location: Must be based in the US and live within commuting distance of hubs in New York, Seattle, Los Angeles, or San Francisco

Salary: $255K – $345K + Equity

Company

hirify.global is the largest livestream shopping platform in North America and Europe, enabling users to buy, sell, and discover items across hundreds of categories.

What you will do

• Own the infrastructure powering AI and ML models for growth, recommendations, trust and safety, and fraud.
• Design and scale low-latency, high-throughput inference infrastructure capable of serving large models.
• Evolve real-time feature pipelines to ensure single-second feedback from behavioral signals.
• Lead the development of distributed training and inference pipelines leveraging GPUs and model/data parallelism.
• Build abstractions, APIs, and developer tools to simplify the iteration of near-realtime features for scientists.
• Optimize system performance through resource utilization management and intelligent feature caching.

Requirements

• Must live within commuting distance of New York, Seattle, Los Angeles, or San Francisco hubs.
• 1+ years of TLM experience developing production machine learning systems at consumer-scale loads.
• 5+ years of hands-on software engineering experience building production systems for consumer-scale loads.
• Professional experience developing software in Python.
• Experience with operational, search, and key-value databases such as PostgreSQL, DynamoDB, Elasticsearch, and Redis.
• Experience with ML-specific tools and frameworks like MLFlow, LitServe, TorchServe, or Triton.

Nice to have

• Familiarity with AWS services including Sagemaker, Lambda, Kinesis, S3, EC2, and EKS/ECS.
• Experience with Apache Kafka and Flink.
• Proficiency with monitoring and logging tools such as DataDog and Grafana.

Culture & Benefits

• Comprehensive health insurance (Medical, Dental, Vision) and 401k with employer match up to 4%.
• Dedicated work-from-home support including setup allowance and monthly cell phone/internet stipend.
• Wellness and childcare allowances, plus lifetime benefits for family planning.
• 16 weeks of paid parental leave with a gradual return-to-work period.
• Monthly budget for dogfooding the app to develop a deep understanding of the product.
• Generous holiday and time-off policy.