Fastino
Distinguished Agent Engineer
San Francisco Bay Area · Hybrid · Principal · Full-time · Posted Oct 19, 2026
- Experience
- 5+ years of software engineering experience, including 3+ years building with LLMs or ML in production.
About the job
Set technical direction and build core agentic systems on Fastino’s specialized language models, from architecture and evaluation to production serving.
What you'll do
- Design and own agent architecture for planning, tool use, memory, and multi-agent orchestration; write core code.
- Benchmark specialized models against frontier LLMs and build evals, telemetry, and feedback loops using customer workloads.
- Improve agent performance and reliability at scale, and guide research, data, and fine-tuning strategy.
What they ask for
- Track record of shipping agentic systems relied on by real users.
- Deep experience across prompt and context engineering, tool and API design, vector DBs, Kubernetes, and inference serving.
- Strong understanding of fine-tuning, evaluations, model failure modes, and latency/cost tradeoffs.
- Experience setting technical direction across teams.
Nice to have
- 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.
Tools
LLMs, ML, vector DBs, Kubernetes, GLiNER
AI focus
Build and evaluate agentic systems using specialized language models; develop agent capabilities, evaluations, telemetry, and fine-tuning strategies.
Model-written summary · the original posting is authoritative