Software Engineer, Agent

The role

You will own the technical delivery of AI agents for enterprises in fraud and risk workflows. You will design, build, and deploy production-grade agents and manage the full development lifecycle from pilot to production.

What you will do

• Design and ship production-grade AI agents.
• Own technical evaluation by designing evaluations and PoCs based on customer data.
• Translate customer edge cases into technical evaluation.
• Act as the technical voice for executive stakeholders.
• Encode operational stakeholder judgement into agents.
• Own the agent development lifecycle end to end.
• Design customized demos and partner with the sales team for technical discovery.
• Shape the long-term roadmap based on deployment patterns.

Required qualifications

• 3-5 years in customer-facing technical roles, forward-deployed or solutions engineering, or software engineering with direct customer exposure
• Strong software engineering fundamentals with a track record shipping end-to-end production systems
• Hands-on experience building with LLMs, including prompt and context engineering, tool use, and evals
• Calibrated instincts about what models can and cannot do reliably
• Strong problem-solving in ambiguous, fast-changing environments
• Ability to communicate complex technical concepts to both engineers and executives

Nice to have

• Familiarity with deploying agentic systems in production
• Domain experience in fraud or risk
• Experience shipping into regulated environments (security reviews, data residency, audits)

Benefits

• Platinum-level medical, dental, and vision insurance
• Unlimited PTO, sick leave, and parental leave
• Up to $100 per month in reimbursement for personal health and wellness expenses
• Up to $200 per month in commuter benefits
• Free lunch and dinner
• 401(k) plan with employer match (eligible after 6 months)
• Meaningful equity

About the company

Variance is teaching machines to make hard judgement calls at scale by building AI agents for risk investigations, fraud, and identity reviews. The company recently raised a $21M Series A.