Variance
Software Engineer, Agent
San Francisco · Full-time · Posted Aug 25, 2026
- Experience
- 3–5 years in customer-facing technical roles, forward-deployed or solutions engineering, or software engineering with direct customer exposure.
About the job
Build and deploy AI agents for enterprise fraud and risk workflows, working directly with customers from technical evaluation through production and ongoing improvement.
What you'll do
- Design, evaluate, deploy, and continuously improve production AI agents using customer workflows and data.
- Lead technical evaluations, proofs of concept, pilots, and customized demos; communicate with customer teams and executives.
- Translate operational judgment and deployment patterns into agent capabilities and product roadmap input.
What they ask for
- Strong software engineering fundamentals and a track record of shipping end-to-end production systems.
- Hands-on experience building with LLMs, including prompt and context engineering, tool use, and evaluations.
- Ability to solve ambiguous problems and communicate technical concepts to engineers and executives.
- Comfort working directly with customers.
Nice to have
- Familiarity deploying agentic systems in production or experience in fraud or risk.
- Experience shipping into regulated environments, including security reviews, data residency, or audits.
Tools
LLMs
AI focus
Build and deploy AI agents for fraud and risk investigations, including agent evaluation, context and tool engineering, and performance tuning against production data.
Model-written summary · the original posting is authoritative