Backend Engineer (US)

Freehand

11d•Remote

About The Position

Freehand is building AI agents that replace the human decision-making and coordination layer above enterprise software. These agents handle analysis, negotiation, prioritization, and execution, serving major clients like Apple, Meta, and GE. The company is looking for individuals who want to work on impactful projects with driven colleagues. As a Backend Engineer, you will be responsible for building the distributed systems, APIs, and AI agent infrastructure that power AI-driven enterprise execution. This involves designing and scaling backend services for agent orchestration, business rule enforcement, deep integration with ERPs and financial systems, and ensuring secure, traceable, and reliable AI actions. The role focuses on building the backend for autonomous systems that handle significant financial risk, including the necessary observability and testing infrastructure.

Requirements

Strong experience building production backend systems.
Strong proficiency in Python, NodeJS, Go, or similar backend languages.
Deep understanding of distributed systems, APIs and microservices, databases (SQL and NoSQL), and message queues / event-driven architectures.
Proven experience designing scalable, fault-tolerant systems.
Strong grasp of consistency, concurrency, and data integrity trade-offs.
Experience working with financial systems, enterprise SaaS platforms, or sensitive/regulated data.
Comfort operating in environments where backend failures have a real business impact.

Nice To Haves

Experience building workflow engines or state-driven systems.
Experience with multi-agent orchestration and agent-to-agent communication protocols.
Familiarity with event sourcing, rule engines, or policy systems.
Knowledge of production debugging at scale and observability tooling.
Contributions to or experience with open-source LLM tooling ecosystems.
Experience with agent observability tooling (LangSmith, Arize, Helicone, or custom trace pipelines) and eval design.
Experience building LLM-powered systems in production; familiarity with agent frameworks (LangChain, CrewAI, or custom).

Responsibilities

Design and build scalable backend services using modern system design principles.
Own critical services that manage procurement, invoice, contract, and payment workflows.
Implement orchestration logic that coordinates AI agents, humans, and enterprise systems.
Build resilient systems with strong guarantees around idempotency, retries, and failure handling.
Build and maintain robust APIs consumed by AI services, frontend apps, and external systems.
Integrate deeply with ERP systems, procurement platforms, and payment gateways and financial rails.
Handle complex data normalisation and transformation across enterprise systems.
Build agent execution runtimes: tool calling, context management, memory, and multi-step reasoning loops.
Implement multi-agent coordination—parallel and sequential workflows with human-in-the-loop escalation.
Instrument agent execution with full trace capture: tool calls, LLM I/O, latency, token usage, and cost.
Design evaluation frameworks for agent output quality, task success rate, and regression detection.
Build automated test harnesses for agent pipelines—unit, integration, and replay-based regression tests.
Define and track agent reliability metrics: task completion rate, escalation rate, cost per workflow, and SLA adherence.
Design systems with enterprise-grade reliability, monitoring, and alerting.
Implement fine-grained access controls, audit logs, and data security best practices.
Ensure backend systems meet compliance requirements for financial and regulated data.
Optimize backend systems for latency, throughput, and cost efficiency.
Design services that scale across global customers and billions of transactions.
Proactively identify and fix bottlenecks in distributed systems.