Staff / Principal Software Engineer
Lead the design and delivery of high-scale backend systems for routing across 200+ LLMs and real-time services.
Remote • Canada
- Full Time
- CA$180,000–260,000/year
- Min. 5 YOE
Browse the full live job inventory for Inworld AI. This page is focused on current openings, while the overview tab highlights role groups and hiring patterns.
Lead the design and delivery of high-scale backend systems for routing across 200+ LLMs and real-time services.
Lead research in foundation models, evaluation, and frontier topics to ship impactful results.
Ambitious researcher leads foundational ML projects, evaluates models, and ships impactful open-ended experiments in a distributed team.
Leads model serving at scale, optimizing latency and throughput across distributed systems.
Lead North America GTM strategy and pipeline, collaborating with product/engineering to translate needs into scalable solutions.
Owns model serving optimization and scalability for real-time multimodal inference at scale, with deep experience in modern serving frameworks and GPU-accelerated backends.
Conduct high-impact research on foundation models, evaluation, and frontier topics to ship learnings.
Lead model serving at scale with optimized inference pipelines, deploying multimodal ML systems in production.
Owns cloud infrastructure design, deployment, and security for AI products, enabling scalable, high-performance services across cloud providers.
Leads product marketing strategy, launches, and GTM content for AI platform enabling developer and enterprise adoption.
Research-focused senior/lead scientist role emphasizing foundation models, evaluation, and full-cycle ownership across multimodal AI research.
Lead research in foundation models and multimodal systems; design experiments, ship results, and influence product strategy.
Deliver scalable ML serving pipelines, optimize latency, and ensure production reliability for large-scale multimodal inference.
Owns back-end platform components, shipping scalable routing and API services for multi-provider AI models.
Lead end-to-end ML serving systems with model optimization and high-throughput, scalable inference.