8+ years of hands-on software engineering experience, including tech lead roles.
Strong architectural skills with a proven track record in scaling production systems.
Production experience with agentic systems and AI training or inference pipelines.
Hands-on experience deploying software on AWS using Kubernetes and Terraform.
Experience building sandboxed execution environments for agent workloads.
Extensive experience with AI coding agents, including task scoping and output review.
Ability to thrive in ambiguity and make strategic decisions without a playbook.
Responsibilities
Define the technical direction for Fastino's platform and contribute to architectural decisions.
Design and build the agent harness, focusing on runtime loops and error recovery.
Develop and scale AI training and inference pipelines, optimizing for latency and cost.
Manage deployment of the Fastino platform into customer-managed AWS VPCs using Kubernetes and Terraform.
Create secure sandboxed execution environments for agent workloads.
Ship full-stack features while tackling complex, ambiguous problems.
Collaborate with AI researchers to transition models from research to production.
Benefits
Flexible work environment with a focus on work-life balance.
Opportunities for professional growth and mentorship.
Collaborative culture that encourages innovation and feedback.
Access to cutting-edge technology and tools.
Health and wellness benefits to support employee well-being.
Full Job Description
Staff Software Engineer
Full-time | San Francisco
What You'll Work On:
Help define the technical direction for Fastino's platform, contributing to the architecture decisions that let us scale without slowing down.
Design and build our agent harness, including the runtime loop, tool calling, context management, and error recovery, plus the eval harnesses that measure agent reliability.
Build and scale our AI training and inference pipelines, pushing on latency, throughput, and cost as usage grows.
Own deployment of the Fastino platform into customer-managed AWS VPCs using Kubernetes and Terraform, including install, upgrade, and observability paths that work in environments we don't control.
Build secure sandboxed execution environments for agentic workloads on Modal Sandboxes.
Ship full-stack features end-to-end while owning the hardest, most ambiguous problems on the team.
Partner closely with AI researchers to take new models from research to production, including deployment, evaluation, and monitoring.
Raise the engineering bar through code reviews, mentorship, and setting practices the rest of the team builds on, including how we work with AI coding agents.
Talk to customers and turn their feedback into product decisions, fast.
What We're Looking For:
Required: 8+ years of hands-on software engineering experience, including time as a tech lead or driving architecture across a team or product.
Required: Strong architectural skills, with a track record of designing and scaling production systems that handle real load.
Required: Production experience with agentic systems, AI training pipelines, or inference pipelines, ideally more than one.
Required: Hands-on experience deploying software on AWS with Kubernetes and Terraform, ideally into customer-managed or multi-tenant environments.
Required: Experience building and running sandboxed execution environments for agent workloads, ideally with Modal Sandboxes.
Required: Extensive experience building with AI coding agents, and a demonstrated ability to guide them to produce clean, production-quality code. You know how to scope tasks, review output critically, and catch what agents get wrong.
Required: You thrive in ambiguity, make good calls without a playbook, and know when to move fast versus when to build for the long term.
Optional: Experience building agent harnesses or frameworks used in production, including familiarity with MCP or similar tool protocols.
Optional: Experience with LangSmith or similar tooling for tracing, evaluating, and monitoring agents.
Optional: Hands-on experience with inference optimization, like batching, quantization, GPU utilization, or serving frameworks such as vLLM, SGLang, or Triton.
Optional: Deep experience with high-concurrency backend systems or low-latency API design.
Optional: Startup experience, ideally as an early engineer helping a team grow.
