Staff SW Engineer

fastino.ai • San Francisco, CA

6d • Onsite

About The Position

Fastino is building the next generation of specialized, efficient LLMs. Its GLiNER family of open-source models has been downloaded more than 50 million times and is used by companies including NVIDIA, Meta, and Airbnb. Fastino has raised $25 million in a seed round and is backed by leading investors.

The Staff Software Engineer will help define the technical direction and architecture of Fastino’s platform. The role involves building agent systems, AI training and inference pipelines, and secure sandboxed execution environments; deploying the platform into customer-managed AWS VPCs; shipping full-stack features; and taking ownership of difficult, ambiguous problems. The engineer will work closely with AI researchers and customers, and raise engineering standards through reviews, mentorship, and practices for working with AI coding agents.

Requirements

• At least 8 years of hands-on software engineering experience, including experience as a tech lead or driving architecture across a team or product.
• Strong architectural skills and a track record of designing and scaling production systems that handle real load.
• Production experience with agentic systems, AI training pipelines, or inference pipelines; ideally more than one of these areas.
• Hands-on experience deploying software on AWS with Kubernetes and Terraform, ideally in customer-managed or multi-tenant environments.
• Experience building and running sandboxed execution environments for agent workloads; Modal Sandboxes experience is ideal.
• Extensive experience building with AI coding agents and guiding them to produce clean, production-quality code, including scoping tasks, critically reviewing output, and catching errors.
• Ability to thrive in ambiguity, make sound decisions without a playbook, and balance speed with long-term considerations.

Nice To Haves

• Experience building production agent harnesses or frameworks, including familiarity with MCP or similar tool protocols.
• Experience with LangSmith or similar agent tracing, evaluation, and monitoring tools.
• Hands-on experience with inference optimization, such as batching, quantization, GPU utilization, or serving frameworks such as vLLM, SGLang, or Triton.
• Deep experience with high-concurrency backend systems or low-latency API design.
• Startup experience, ideally as an early engineer helping a team grow.

Responsibilities

• Help define the technical direction and architecture of Fastino’s platform.
• Design and build the agent harness, including its runtime loop, tool calling, context management, error recovery, and reliability evaluation harnesses.
• Build and scale AI training and inference pipelines, improving latency, throughput, and cost as usage grows.
• Deploy the Fastino platform into customer-managed AWS VPCs using Kubernetes and Terraform, including installation, upgrades, and observability in environments the team does not control.
• Build secure sandboxed execution environments for agentic workloads on Modal Sandboxes.
• Ship full-stack features end-to-end and own difficult, ambiguous problems.
• Partner with AI researchers to move new models from research into production, including deployment, evaluation, and monitoring.
• Raise engineering standards through code reviews, mentorship, and practices for working with AI coding agents.
• Talk to customers and translate their feedback into product decisions.

What This Job Offers

• Job Type: Full-time
• Career Level: Senior
• Education Level: No Education Listed