2 days ago
Remote, United States +4 moreSenior
Responsibilities
- Design and ship multi-step agentic systems for KYB, underwriting, case review, and risk-monitoring workflows.
- Architect durable, stateful agent graphs with retries, safe fallbacks, and tool-using or human-in-the-loop patterns.
- Build retrieval systems using chunking, hybrid search, reranking, and grounded citations across financial and business data.
- Own offline and online evaluation systems, including golden sets, regression suites, LLM-as-judge evaluations, A/B tests, shadow evaluations, and red-teaming.
- Integrate agents with production systems through typed tools, MCP servers, and existing decisioning, case-management, and crosswalking services.
- Drive production MLOps for agents, including deployment, versioning, traffic shaping, cost and latency controls, observability, and incident playbooks.
- Partner with security, compliance, and legal teams to maintain SOC 2, GDPR, CCPA, and fair-lending requirements.
- Translate ambiguous product opportunities into agent designs, prototypes, and shipped features.
- Mentor engineers on agent patterns, prompt engineering hygiene, evaluation practices, and LLM failure modes.
Requirements
- 8+ years of professional software engineering experience, including at least 2 years building production LLM or agentic systems.
- Strong software engineering experience across front-end systems, APIs, asynchronous patterns, queues, databases, and distributed-system failure modes.
- Ownership experience for major production features or subsystems and experience mentoring junior engineers.
- Experience with event-driven systems, including enrichment, retries, dead-lettering, and backpressure.
- Experience managing containerized applications with Kubernetes, EKS, ArgoCD, operators, and Kustomize.
- Hands-on experience with a modern agent framework, with LangGraph strongly preferred, and a record of shipping reliable agents.
- Experience building and using golden sets, offline and online evaluations, and ship/no-ship evaluation decisions.
- Production MLOps experience deploying LLM workloads under latency, cost, and reliability constraints with instrumentation.
- Strong Python proficiency and comfort with TypeScript and Node.js.
- Experience explaining agent trade-offs to product, security, and customer stakeholders.
- Bonus: experience in fintech, lending, payments, KYB/KYC, fraud, AML, or other regulated domains.
- Bonus: experience building MCP servers or structured LLM tool interfaces.
- Bonus: classical machine learning experience in ranking, scoring, or calibration.
- Bonus: experience with explainable or auditable AI workflows, regulated environments, or fair lending.
- Bonus: open-source contributions to agent frameworks, evaluation tooling, or retrieval libraries.
- Bonus: deep AWS experience with EKS, MSK, RDS, S3, or Lambda and infrastructure as code with Terraform.
Benefits
- Remote work arrangement, with travel to Orlando at least twice per year for town halls and team collaboration plus Orlando orientation.
- Hybrid work option for Orlando associates.
- Medical, dental, and vision health care plan.
- 401(k) and IRA retirement plans.
- Life insurance.
- Flexible paid time off.
- Nine paid holidays.
- Family leave.
- Free food and snacks for Orlando associates.
- Wellness resources.
Tech Stack
Categories
About Worth AI
Worth AI builds a SaaS platform that automates onboarding and underwriting for business credit, using AI-driven risk models, real-time SMB data, and continuous portfolio monitoring. It sells to banks, lenders, and fintechs that need faster credit decisions and portfolio visibility. Founded in 2023 and headquartered in Winter Park, Florida, the company is privately held.