Platform Engineer - Inference

About SubconsciousAgents are eating the economy, but it's still the early days. Token useage is increasing 2,500% year over year, agents token consumption is growing 7x faster than humans, and adoption of agentic systems is on the rise across professions. All signs point to these trends continuing, as agentic workloads become irreplacable across software, cybersecurity, legal, finance, HR, sales, and science tasks. We are building the foundation. Subconscious is an inference platform specifically designed to power long-running agents. For tasks that consume 200k+ tokens, our inference system delivers unparalleled speed, accuracy, and cost efficiency. As agents proliferate, Subconscious will be a provider in every agent stack. About the roleYou will provide the battle-tested infrastructure experience needed to scale our platform to hundreds of thousands of users. Today, we serve billions of tokens per day. With your contributions, we'll serve trillions. This is a ground-floor role. You will shape the product, technology, and engineering culture. We expect the person who fills this role to grow into a leadership position. ResponsibilitiesOwn the reliability, performance, observability, uptime, load balancing, and security of inference workloads.Work closely with our research team to make new inference optimizations and open source model support broadly available to customers.Contribute to the technical direction of our inference platform including major architecture and build vs. buy decisions.Help build the product factory that makes our team ship code like a team 10x our size - including human-driven process, CI/CD, and agent guardrails.Establish durable engineering culture through design docs, architecture reviews, mentorship, and hands-on implementation.You will work across our inference stack, from the user-facing platform to GPU cache optimization. Role requirements5+ years in Platform, Infrastructure, or Inference engineering rolesExperience running Kubernetes at scaleExperience running AWS at scaleDeep observability experience - including Datadog (Prometheus and Grafana are a plus)Expert in deployment jujitsu - zero downtime, rollbacks, blue/green, canary, etc. - we want someone with battle scarsProficient in Terraform, CI/CD pipelines, and GitOps workflowsExperience with SDLC security and compliance processesStaff-level judgment - you can define ambiguous problems, make pragmatic tradeoffs, influence without authority, and leave both systems and teams better than you found them. You can tell a good story with data.Product sense - you solve problems by working backwards from the end-user and business requirements.You have character, a sense of humor, and compassion. You are someone we are excited to introduce to our partner.Nice to haveYou have worked in startups beforeYou have worked on AI systems that serve trillions of tokens per dayExperience with vLLM, SGLang, or NVIDIA DynamoExperience with BYOC (bring your own cloud) implementationsExperience with SOC 2 - ideally having contributed to achieving complianceExperience with GCP or AzureExperience with agent-driven software delivery at scaleLocationWe are based in Boston, MA, and are in the office 5 days a week. For an exceptional candidate, we are willing to consider remote work. CompensationWe can't build this company without you, and we want you to be a meaningful owner alongside us. Your equity will reflect that. Salary will be between $180k-$230k with significant equity ownership. BenefitsWe offer full medical, dental, and vision coverage, plus unlimited PTO. We order Shy Bird on Wednesdays in the office.