Senior Agent Engineer — Architect Scalable AI Agents

fastino.ai; San Francisco (CA); On-site; USD 180,000 - 240,000; Full time

Job summary

Fastino is building specialized, efficient language models to outperform general models on targeted tasks. As Distinguished Agent Engineer, you will set the technical direction for agent construction on Fastino models, write core code, and raise the bar for the team.

You have shipped agentic systems used by real customers and possess strong opinions on what works. You will design architectures for agentic systems, benchmark performance, and collaborate with research to translate architectures

Qualifications

• 5+ years of software engineering, with 3+ years building with LLMs or ML in production.
• Track record shipping agentic systems used by real users.
• Deep experience across the stack: prompt engineering, tool/API design, vector DBs, Kubernetes, inference serving.
• Strong understanding of model behavior: fine-tuning, evals, latency/cost tradeoffs.
• Experience setting technical direction across teams, not just within one project.
• Clear writing; able to simplify complex systems.
• Bonus: high-concurrency microservices for agent workloads.
• Bonus: familiarity with GLiNER or information extraction architectures.

Responsibilities

• Design and own the architecture for agentic systems built on Fastino's small, fast models.
• Figure out where specialized models beat frontier LLMs inside agent loops, with benchmarks and workloads.
• Build evals, telemetry, and feedback loops to show agent improvement or regression.
• Partner with research to turn new model architectures into agent capabilities and guide future work.
• Make agents fast and reliable at scale: low latency inference and high concurrency serving.
• Drive data and fine-tuning strategy for tasks like tool calling, extraction, and routing.

Skills

LLMs in prod

Agentic systems

System design

Kubernetes

Inference serving

Tool design

Prompt engineering

Tools

Kubernetes

API design

Vector DBs

Job description

Fastino is building specialized, efficient language models to outperform general models on targeted tasks. As Distinguished Agent Engineer, you will set the technical direction for agent construction on Fastino models, write core code, and raise the bar for the team.

You have shipped agentic systems used by real customers and possess strong opinions on what works. You will design architectures for agentic systems, benchmark performance, and collaborate with research to translate architectures