Note: The job is a remote job and is open to candidates in USA. Eleven Recruiting is a specialized technology staffing agency supporting professional and financial services companies. They are seeking a fully remote Staff AI Engineer to design and build complex AI systems, mentor engineers, and set architectural standards for multi-agent workflows.
Responsibilities
- Design and build the most technically demanding parts of the system yourself, working in an AI native, agentic coding workflow as your daily practice, not just directing others
- Set the architecture for multi-agent coordination across complex, long-running workflows with human-in-the-loop oversight, including agent state machines, tool routing, context windowing, and retry logic for processes that can run for minutes or hours
- Own the durable state and run-record layer for long-running agentic workflows: state hydration, failure handling, checkpoint/resume, and recovery across distributed services
- Build production-grade pipelines that extract, classify, and validate structured documents across a wide range of formats and quality levels, and define the validation layer that turns raw extraction into output the business can trust
- Build the measurement backbone for the platform: task completion rates, accuracy attribution, cost tracking, and regression detection, so that "is this good enough to ship" is backed by data, not opinion
- Design the supervision layers, validation rules, human review gates, and audit trail needed to make non-deterministic AI output trustworthy for professionals who can't tolerate errors
- Set the framework the team uses to reason about cost, accuracy, and latency trade-offs across use cases and peak-volume periods
- Mentor engineers, raise the bar in design and code review, and help spread an AI native, agentic engineering culture across the broader team, reducing key-person risk by leaving systems more legible than you found them
Skills
- 8+ years building and operating backend systems in production environments where uptime and correctness are critical
- A track record of leading the design of complex, distributed, or high-scale systems from architecture through deployment and ongoing operations
- Hands-on production experience with agent orchestration frameworks (such as LangGraph) and long-running, stateful, multi-step agentic workflows. You need to have shipped this class of system, not just studied it
- Demonstrated technical leadership beyond your own commits: setting patterns and standards, driving cross-functional initiatives, mentoring engineers, and influencing decisions across an organization
- Strong experience with relational databases (PostgreSQL or similar): schema design, query optimization, data modeling, and migrations
- Hands-on work with event-driven architectures: message queues, async processing, and distributed job execution
- Production experience with AWS (Lambda, SQS, S3, ECS) or an equivalent cloud platform
- Comfort reading and writing both TypeScript and Python, or clear evidence of picking up a second language quickly
- Experience across the full software delivery lifecycle: design, implementation, testing, deployment, monitoring, and incident response
- Sound judgment on build-versus-buy decisions, with the ability to make and defend architectural trade-offs under real time and cost constraints
- Familiarity with modern agent/LLM tooling such as LangChain, vector databases, and cloud-based model platforms (e.g., AWS Bedrock)
- Created and scaled products from 0-to-1 that also generated revenue
- Depth in multi-agent coordination specifically: designing supervision, routing, and hand-off between cooperating agents
- Familiarity with RAG architectures, vector databases, or document processing pipelines
- Experience with multi-tenant SaaS architecture: schema isolation, tenant-scoped data, and access control
- Background in document intelligence: OCR, structured extraction from PDFs, and form understanding
- Experience standing up evaluation, observability, or quality systems for ML/LLM products
- Work in a regulated or high-trust domain (finance, legal, healthcare, tax) where output correctness is non-negotiable
- Open-source contributions, technical writing, or other public evidence of engineering depth
Company Overview