Staff SW Engineer
fastino.ai12 days ago
Responsibilities
- Define Fastino’s technical direction and make architecture decisions for a scalable platform.
- Design and build the agent harness, including runtime loops, tool calling, context management, error recovery, and evaluation harnesses.
- Build and scale AI training and inference pipelines for latency, throughput, and cost.
- Deploy and operate the Fastino platform in customer-managed AWS VPCs using Kubernetes and Terraform, including installation, upgrades, and observability.
- Build secure sandboxed execution environments for agent workloads using Modal Sandboxes.
- Ship full-stack features, solve ambiguous technical problems, and partner with AI researchers to move models from research to production.
- Raise engineering standards through code reviews, mentorship, development practices, and effective use of AI coding agents.
- Work with customers and incorporate their feedback into product decisions.
Requirements
- 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 designing and scaling production systems handling real load.
- Production experience with agentic systems, AI training pipelines, or inference pipelines.
- Hands-on AWS deployment experience with Kubernetes and Terraform, preferably in customer-managed or multi-tenant environments.
- Experience building and operating sandboxed execution environments for agent workloads, preferably with Modal Sandboxes.
- Extensive experience building with AI coding agents and guiding them toward clean, production-quality code.
- Ability to make sound decisions in ambiguous environments and balance speed with long-term engineering quality.
- Optional experience with production agent harnesses or frameworks, MCP or similar tool protocols, LangSmith or similar agent tooling, inference optimization, vLLM, SGLang, Triton, high-concurrency backend systems, low-latency API design, or startup environments.
Benefits
- Full-time role based in San Francisco.
Tech Stack
Categories
About fastino.ai
Fastino builds task‑optimized small language models and Pioneer, a fine‑tuning and inference system that lets developers deploy and continuously improve open‑source models without code. It targets enterprise AI teams that need accurate, fast, and secure on‑prem or cloud deployments, including near‑instant CPU inference. The privately held company’s research includes the open‑source GLiNER/GLiNER2 models with millions of downloads, and it raised a seed round in 2025.