Agent Engineer

At Variance, we are using disruptive technologies to solve some of our digital age's oldest and most complex problems, using safe and effective AI. Your work will directly contribute to helping fraud and Risk & Compliance teams spend less time on repetitive manual reviews and investigations, allowing them to focus on what matters most. We are rapidly growing, serving some of the largest and fastest-growing social media, online and financial services platforms.

What you'll do

Design and ship production-grade AI agents. You will build agents that make high-stakes decisions inside our customers' risk operations: fraud investigations, KYB and KYC reviews, AML workflows, and marketplace integrity.

Own the agent development lifecycle end to end. You will take agents from initial pilot through deployment and continuous iteration. That means scoping the workflow with the customer, engineering the context and tools the agent needs, building evals that actually measure decision quality, and tuning performance against real production data. You set the bar for what a well-built agent looks like.

Work directly with enterprise customers. You will sit with risk, fraud, and compliance leaders at some of the world's largest companies to understand how their investigators actually work, then encode that judgment into agents. You will see your work change how these teams operate within weeks.

Shape the platform. Your work in the field drives the evolution of Variance's core platform, including the context engine, entity graph, and agentic review automation. The patterns you discover building for one customer become the primitives every customer gets.

What you'll bring

• Strong software engineering fundamentals and experience shipping end-to-end production systems

• Strong people and communication skills. Experience communicating complex technical concepts to non-technical stakeholders and executives.

• Hands-on experience building with LLMs, including prompt and context engineering, tool use, RAG, and evals, plus calibrated instincts about what models can and cannot do reliably

• Strong problem-solving in ambiguous, fast-changing environments. You can take a fuzzy customer workflow and turn it into a working system

• Comfort working directly with customers and translating business needs into technical decisions

• Excellent written and verbal communication with both technical and non-technical audiences

• Degree in Computer Science or a related field, or equivalent professional experience

Even better

• Experience building or deploying agentic systems in production

• Familiarity with eval frameworks and a rigorous approach to measuring agent quality

• Domain experience in fraud, risk, identity, compliance, trust and safety, or financial services

• Experience shipping into regulated environments, including security reviews, data residency requirements, and audits

What success looks like

• Agents you build hold up in production. They are accurate, reliable, and trusted by the operators who work alongside them

• Pilots convert because the system demonstrably works on the customer's real data and real edge cases

• Customer-specific solutions become reusable platform capabilities

• Enterprise buyers see Variance as a technical partner, not just a vendor

What we offer

• Health care: 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

• Free lunch and dinner

• 401(k) plan

• Meaningful equity in a fast-growing, Series A company

This is an in-person position. Our office is located in San Francisco, CA.

We evaluate all applicants consistently without regard to race, color, religion, gender, national origin, age, disability, veteran status, pregnancy, gender expression or identity, sexual orientation, citizenship, or any other legally protected class. We encourage you to apply even if your experience doesn't precisely match the job description.