AI Engineer

Location: On-site in Atlanta, Georgia, United States

Company

hirify.global is a consulting company hiring an AI Engineer to build production agentic systems.

What you will do

• Design and build multi-step, multi-agent workflows from initial design through production.
• Compose agents into reliable pipelines integrating external APIs, internal services, data sources, typed tools, and service endpoints.
• Design, version, test, and evaluate prompts and agent behaviors, including coordination, memory, state, and human review checkpoints.
• Build evaluation suites and regression checks measuring trajectory and outcome quality.
• Harden, instrument, and debug long-running non-deterministic workflows using tracing, logs, cost, and latency telemetry.
• Contribute reusable agentic-system patterns and partner with product and engineering teams to translate business requirements into practical designs.

Requirements

• Production-grade Python software engineering fundamentals, including clean tested code, async patterns, and long-running stateful processes.
• Experience with agentic or LLM-driven systems in production or near-production settings, including tool use, multi-step reasoning, or agent-to-agent handoffs.
• Experience composing multi-step or multi-agent workflows, managing shared state, chaining tool calls, and handling failures and retries.
• Practical prompt-engineering skills, including designing system messages and improving prompts against evaluations.
• Experience integrating external APIs and services, including REST, authentication, error handling, and partial-failure design; experience building model- or agent-called tools, function interfaces, schemas, or service endpoints.
• Ability to build evaluation suites, create ground truth, and explain what evaluations proved.
• Strong debugging skills for distributed and non-deterministic systems, including failures spanning multiple agents or services.
• Meaningful unit, integration, and scenario-level tests for complex stateful systems.
• Familiarity with agent or LLM observability, including tracing, logging, or monitoring model and tool calls.
• Backend engineering background with APIs, queues, and databases, plus exposure to multi-tenant systems and data-isolation concerns.

Nice to have

• Experience with durable or long-running workflow execution where state survives restarts, retries, or partial failures.
• Familiarity with working memory, long-term memory, and context-window management.
• Experience with retrieval-augmented generation and reranking, including measuring retrieval impact.
• Exposure to human-in-the-loop patterns such as approval steps, escalation policies, and review workflows.
• Experience with agent orchestration frameworks or patterns such as LangGraph.
• Familiarity with prompt-injection and adversarial risks in agent and retrieval systems and their mitigation.
• Comfort working against an SDK or framework abstraction and understanding its constraints and gaps.
• Open-source contributions to agent frameworks or related tooling.

Culture & Benefits

• On-site work in Atlanta, Georgia.
• Product-facing collaboration with product and engineering teams.
• Focus on practical, reliable, and governable agentic systems.