Note: The job is a remote job and is open to candidates in USA. Flex is a growth-stage FinTech company headquartered in NYC, focused on revolutionizing the rent payment experience. They are seeking a Staff AI Engineer to lead the development of AI systems and tools that enhance workflows across the organization, while also mentoring teams and ensuring the successful implementation of AI capabilities.
Responsibilities
- Design, implement, and maintain the agent platform including orchestration, tool execution, sandboxed code runtimes, observability, and the developer-facing SDKs and UI
- Design and develop new APIs, SDKs, and developer surfaces that let other teams onboard agents quickly and safely, with strong defaults for evals, guardrails, human-in-the-loop review, and audit
- Scale the platform to support a growing catalog of agents, skills, and MCP integrations across Flex while maintaining performance, reliability, and cost efficiency
- Continuously improve our daily operations with automation, tooling, design evolution, and observability, including agent-trace visibility, evaluation pipelines, and sandbox runtime monitoring
- Work closely with cross-functional teams to identify high-leverage AI use cases and turn them into production-ready agents on the platform
- Set the bar for AI-assisted engineering practices and responsible AI use across Flex, mentor engineers on how to design, build, and operate agentic systems, and bring outside innovation back into our roadmap
Skills
- 6+ years of experience in software development or a related field, with at least 2+ years building production AI or agentic systems
- Experience in technical leadership, guiding engineering teams through complex projects
- Hands-on experience with coding CLIs and AI dev tools (Claude Code, Codex, OpenCode, Cursor, or equivalents) - both as a daily-driver user and as a builder integrating them into team workflows
- Experience with agent infrastructure and code-execution sandboxes (Modal, E2B, Cloudflare Sandboxes, Daytona, or Firecracker/gVisor-based runtimes), with a clear point of view on isolation, scaling, and cost trade-offs
- Experience building AI-first workflows end-to-end, including LLM application design, prompt and context engineering, RAG, and human-in-the-loop patterns
- Experience creating and managing agents and agent platforms, including multi-agent orchestration (LangGraph, custom planners, sub-agent patterns), tool/skill registries, and MCP-based integrations
- Experience with eval frameworks and offline/online evaluation of agent quality, plus observability and tracing for non-deterministic systems
- Experience with Java, Python, Golang, or TypeScript/Node.js
- Strong experience with relational SQL and NoSQL databases, such as MySQL/PostgreSQL/DynamoDB
- Experience designing and developing fault-tolerant and scalable distributed systems, including workflow and job-orchestration engines
- Experience with AWS cloud services: ECS/EKS, Lambda, API Gateway, VPC, RDS, etc
- Infrastructure as code (AWS CLI, AWS CDK/Terraform)
- Strong communication skills with the ability to understand and explain technical issues to a non-technical audience
- Follow engineering best practices as well as propose new ones - especially around responsible AI use, guardrails, and security for agentic systems
- Bonus: experience with model and prompt evaluation tooling, secure tool-use sandboxing, retrieval and vector stores, and operating multi-tenant AI platforms at scale
Benefits
- Competitive medical, dental, and vision
- Company equity
- 401(k) plan with company match
- Unlimited paid time off + 13 company paid holidays
- Parental leave
- Free Flex subscription
- Competitive compensation + company equity
- Unlimited PTO
Company Overview
Company H1B Sponsorship