Member of Technical Staff, AI Agents
About the role
Role as one of the first engineers at Socratix AI to build production-grade AI agents for fraud and financial crime investigations, shaping the technical foundation and strategy with founders.
Responsibilities
- Build agents end to end: LLM orchestration, tool use across a growing set of MCP integrations, retrieval, and multi-agent workflows that automate real investigations.
- Own the layer that makes agents trustworthy — eval harnesses, guardrails, audit trails, human-in-the-loop review.
- Ship fast and close to users: code in prod your first week, direct customer contact, your work catching actual fraud.
- Experiment relentlessly. New models, new techniques, new tooling — you'll have license to try everything and keep what wins.
- Turn frontier into product. You'll spend real time probing what the newest models can do, then ship the parts that survive contact with real fraud cases.
- Shape roadmap and strategy with the founders. Small team, zero bureaucracy, maximum ownership.
Qualifications
- 2–4 years of engineering experience or a portfolio that makes that line irrelevant.
- You've shipped real things with LLMs — production systems, prototypes with users, obsessive side projects.
- Deep engineering fundamentals. Frameworks are details you pick up in a weekend (we're mostly Python on AWS).
- A systems thinker who reasons about data flow, latency, cost, and failure modes for distributed systems with nondeterministic components.
- Prior startup experience is a plus.
- Curiosity about fintech, fraud, or building AI where the stakes are real and regulated.
Skills
Benefits
- Competitive salary and equity benchmarked to top tech companies.
- Paid meals during workdays.
- 100% health, dental, and vision coverage.
- Hybrid schedule - in-office 3 days a week.
- Commuter Benefits
- Unlimited PTO.
About Socratix AI
AI coworkers for fraud and risk teams.
Socratix builds AI coworkers for fraud and risk teams so that humans don't have to spend their days drowning in alerts and spreadsheets. Today, fraud and risk teams at fintechs and banks are overwhelmed. Analysts jump between tools, manually stitch together context, and make judgment calls under pressure, often for hundreds of alerts a week. Too much of their work is slow, repetitive, and error-prone. We're here to change that. Socratix gives fraud and risk teams AI coworkers that investigate alerts in real time, replacing manual reviews with fast, explainable decisions. Socratix agents plug into existing workflows and reason across signals just like human analysts to help teams reduce fraud losses, minimize false positives, and scale operations without scaling headcount. We've seen this problem firsthand. At DoorDash, Riya helped save $30M+ a year by building smarter fraud detection and investigation tooling, and at Unit21, she built products for analysts that made them 3X faster. We're able to build and sell enterprise-grade software. At Cruise, Satya built scalable AI systems powering petabyte-scale data, and at LinkedIn, he built enterprise products from 0 to 1 generating $50M+ in incremental revenue. Now, the two of us are teaming up to eliminate the manual toil in fraud and risk. We're obsessed with fraud, LLMs, real-world automation, and the messy edge cases traditional ML has trouble handling. We believe that every fraud analyst should have an AI coworker - and the future of fraud will involve combining human-level reasoning with machine-speed execution.
More open roles at Socratix AI
- Founding GTM Lead, AI Agents2w agoHybrid (Mountain View, CA)