AI Engineer - Forward Deployed

Moring Ai•Atlanta, GA

1d•Onsite

About The Position

Moring.ai is hiring an AI Engineer for a forward-deployed, individual-contributor role building enterprise AI applications and shipping them into production. The engineer will work across the product and platform stack, building AI capabilities for regulated, compliance-heavy enterprise customers and contributing to the primitives underneath those capabilities. The role involves owning features from design through deployment and operation, while working closely with senior engineers on architecture. This is a customer-facing role: the engineer will embed with enterprise client teams to understand their workflows, systems, and security constraints; integrate and deploy AI solutions in customer AWS accounts and private networks; support demos and working sessions; and translate field learnings into product improvements. The position is based 100% onsite in Atlanta, Georgia, with travel of up to 25% to customer sites. Applicants must be authorized to work in the United States; visa sponsorship is unavailable.

Requirements

3–6 years of software engineering experience shipping production systems in backend, platform, or full-stack roles.
Solid AWS experience, including ECS or Lambda, IAM, and networking.
Familiarity with infrastructure as code, such as Terraform or CDK.
Strong Python skills and production engineering practices, including testing, code review, and observability.
Good grounding in APIs, data, and distributed systems.
Recent, demonstrable hands-on AI experience building agents, RAG pipelines, or LLM applications; production work, serious side projects, and open source work count.
Working experience with at least one agent framework, such as LangGraph, CrewAI, or a comparable framework, and major model APIs such as Anthropic, OpenAI, or Bedrock.
Practical understanding of LLM behavior, context management, token economics, cost and latency trade-offs, and testing nondeterministic systems.
Understanding of RAG, especially retrieval, and how to measure whether it is working.
Willingness to work directly with enterprise customers and communicate trade-offs in plain language.
Authorization to work in the United States; visa sponsorship is not available.

Nice To Haves

Experience integrating enterprise systems, such as SSO, enterprise APIs, data platforms, or systems of record.
Familiarity with MCP, including its current limitations and security considerations.
TypeScript experience for product-surface work.
Prior startup experience shipping quickly with small teams.
Customer-facing, solutions engineering, or technical consulting experience with enterprise customers.

Responsibilities

Build and ship agents, agentic workflows, and LLM-powered features from prototype through production.
Develop retrieval systems, including chunking and embedding strategies, vector and hybrid search, and measurement of retrieval quality.
Integrate Anthropic, OpenAI, and Bedrock model APIs, and use tools and data through the Model Context Protocol (MCP).
Work directly with enterprise client teams to understand their workflows and systems and build solutions for their environments.
Integrate with enterprise identity and SSO systems, APIs, data warehouses, and systems of record.
Deploy solutions into customers' AWS accounts and private networks while accounting for their security models.
Support demos and working sessions with client engineers and business stakeholders.
Convert customer learnings, recurring requests, integration patterns, and platform gaps into product improvements.
Contribute to the model-access layer, agent orchestration, and evaluation harness.
Build tracing, cost and latency dashboards, and quality monitoring.
Own features from design through deployment and operation, including writing tests, evaluations, and observability.