Distinguished Agent Engineer
Fastino
About the role
Distinguished Agent Engineer
Full-time | San Francisco or Remote
About Fastino
We're building specialized, efficient language models that beat big general models on the tasks that matter. Our team includes alumni from Google Research, Apple, Stanford, and Cambridge.
Our open source GLiNER models have been downloaded 50M+ times and are used by teams at NVIDIA, Meta, and Airbnb.
We've raised $25M (covered in TechCrunch) from Microsoft, Khosla Ventures, Insight Partners, GitHub CEO Thomas Dohmke, Docker CEO Scott Johnston, and others.
The Role
This is one of our most senior IC engineering role. You'll set the technical direction for how agents get built on Fastino models, write a lot of the core code yourself, and raise the bar for everyone around you. You've built agentic systems that real users depend on, and you have strong opinions about what works.
What You'll Work On
Design and own the architecture for agentic systems built on Fastino's small, fast models: planning, tool use, memory, and multi-agent orchestration.
Figure out where specialized models beat frontier LLMs inside agent loops, and prove it with benchmarks and real customer workloads.
Build the evals, telemetry, and feedback loops that tell us when agents are getting better (or worse) and why.
Partner with research to turn new model architectures into agent capabilities, and shape what research works on next.
Make agents fast and reliable at scale: low latency inference, high concurrency serving, graceful failure handling.
Drive data and fine-tuning strategy for agent specific tasks like tool calling, extraction, and routing.
What We're Looking For
5+ years of software engineering experience, with 3+ years building with LLMs or ML in production.
A track record of shipping agentic systems that real users rely on, and the scars to prove it.
Deep experience across the stack: prompt and context engineering, tool and API design, vector DBs, Kubernetes, and inference serving.
Strong understanding of model behavior: fine-tuning, evals, failure modes, and latency/cost tradeoffs.
Experience setting technical direction across teams, not just within one project.
You write clearly and make complicated systems feel simple.
Bonus: experience building high concurrency microservices for agent workloads.
Bonus: familiarity with GLiNER or other information extraction architectures.
Bonus: open source contributions, papers, or talks on agents or LLM systems.
Responsibilities
- Set technical direction and own architecture for agentic systems built on Fastino models.
- Evaluate specialized models in agent workflows using benchmarks and customer workloads.
- Build evaluation, telemetry, and feedback systems for agent performance.
- Partner with research to translate model architectures into agent capabilities.
- Improve agent speed, reliability, and scalability.
- Drive data and fine-tuning strategies for agent tasks.
Qualifications
- 5+ years of software engineering experience, including 3+ years building LLM or ML systems in production.
- Track record of shipping agentic systems used by real users.
- Experience with prompt and context engineering, tool and API design, vector databases, Kubernetes, and inference serving.
- Strong understanding of fine-tuning, evaluations, model failure modes, and latency-cost tradeoffs.
- Experience setting technical direction across teams.
- Clear written communication skills.
Skills mentioned
About Fastino
We believe the future of AI will be built on specialized small language models. To advance that mission, we're building Pioneer. Pioneer is the world's first agentic fine-tuning and inference system. With Pioneer, any developer can fine-tune, deploy, and continuously improve open source small language models in minutes, without writing a single line of code. Our research includes GLiNER and GLiNER2, open-source models with millions of downloads used by thousands of developers and organizations worldwide for entity extraction, text classification, and structured data extraction.
H-1B sponsorship history
Historical employer filing data was found for Fastino. The employer record includes 3 historical certified applications. This is employer-level history, not a guarantee that this role currently offers sponsorship.