Distinguished Agent Engineer

fastino.ai • San Francisco, CA

4d

About The Position

Fastino is building specialized, efficient language models designed to outperform large general-purpose models on important tasks. Its open-source GLiNER models have been downloaded more than 50 million times and are used by teams at NVIDIA, Meta, and Airbnb. The company has raised $25 million from investors and industry leaders.

The Distinguished Agent Engineer is one of Fastino’s most senior individual-contributor engineering roles. This person will set technical direction for building agents on Fastino models, write core code, and raise engineering standards across the team. The role focuses on agentic systems that real users depend on and requires a strong understanding of what works in practice.

The engineer will own the architecture of agentic systems built on Fastino’s small, fast models, including planning, tool use, memory, and multi-agent orchestration. They will assess where specialized models outperform frontier LLMs in agent loops, validate results through benchmarks and customer workloads, and build evaluation, telemetry, and feedback systems. They will also partner with research to translate model architectures into agent capabilities, improve the speed and reliability of agents at scale, and guide data and fine-tuning strategies for agent-specific tasks. The role is full-time and can be based in San Francisco or remote.

Requirements

• At least 5 years of software engineering experience, including at least 3 years building with LLMs or machine learning in production.
• Track record of shipping agentic systems that real users rely on.
• Deep experience across the stack, including prompt and context engineering, tool and API design, vector databases, Kubernetes, and inference serving.
• Strong understanding of model behavior, including fine-tuning, evaluations, failure modes, and latency-cost tradeoffs.
• Experience setting technical direction across teams.
• Clear writing and ability to make complex systems understandable.

Nice To Haves

• Experience building high-concurrency microservices for agent workloads.
• Familiarity with GLiNER or other information extraction architectures.
• Open-source contributions, papers, or talks on agents or LLM systems.

Responsibilities

• Design and own architecture for agentic systems built on Fastino models, including planning, tool use, memory, and multi-agent orchestration.
• Determine where specialized models outperform frontier LLMs in agent loops and demonstrate results with benchmarks and real customer workloads.
• Build evaluations, telemetry, and feedback loops to track when and why agents improve or regress.
• Partner with research to turn new model architectures into agent capabilities and help shape future research priorities.
• Improve agent speed and reliability at scale, including low-latency inference, high-concurrency serving, and graceful failure handling.
• Drive data and fine-tuning strategy for agent-specific tasks such as tool calling, extraction, and routing.
• Write core code, set technical direction across teams, and raise engineering standards.

What This Job Offers

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