AI Engineer

Moring Ai•Alpharetta, GA

1d•$60,000 - $80,000•Onsite

About The Position

Moring.ai builds enterprise AI applications and agents for regulated and compliance-heavy industries, deploying them inside customers’ cloud environments and existing systems. The company is early-stage, lean, and profitable. The AI Engineer will help build the AI platform and the agents that run on it, primarily working on platform systems such as the LLM gateway, agent runtime, MCP servers, registry, evaluations, and observability. The engineer will own features end to end, with design guidance and review from a tech lead and architect, and will also work with an enterprise customer—often alongside a senior engineer—within the customer’s environment and security constraints. The role involves deploying software into customer cloud accounts, including bank environments that may have no internet egress, require audit trails on model calls, and require security approval before launch. This is an individual-contributor role where leadership is demonstrated through building. The position is 100% on-site in Alpharetta, Georgia, with travel of up to 10% to customer sites. Candidates must be authorized to work in the United States; immediate H-1B transfer is not available. For candidates on OPT, the company can apply for H-1B next year, and candidates should have prior work experience, such as two to three years in India or the United States.

Requirements

2–5 years of software engineering experience shipping production systems in backend, platform, or full-stack roles.
Strong Python skills and production engineering practices, including testing, code review, and observability.
Good grounding in APIs, data, and distributed systems.
Working knowledge of AWS, including ECS or EKS, Lambda, IAM, and networking.
Some exposure to infrastructure as code, such as Terraform or CDK.
Hands-on AI work from roughly the last year, such as building agents, RAG pipelines, or LLM applications; candidates must be able to discuss what they built and what failed. Production work, serious side projects, and open-source work count.
Experience with major model APIs such as Anthropic, OpenAI, or Bedrock, and at least one agent framework such as LangGraph, CrewAI, or a comparable framework.
Practical understanding of LLM behavior, including context management, token costs, latency trade-offs, and testing nondeterministic systems.
Familiarity with RAG and MCP.
Ability and willingness to work directly with enterprise customers and explain trade-offs in plain language.
Curiosity about how large organizations work, including their constraints and review processes, and willingness to work within them.
Authorization to work in the United States. Immediate H-1B transfer is not available; OPT candidates should have prior work experience.

Responsibilities

Build LLM gateway features, including routing, caching, rate limits, per-customer model rules, and cost tracking.
Build parts of the agent runtime, including agent startup, execution, state management, versioning, and rollback.
Build MCP servers for tools and data inside customer environments, with appropriate scopes and security.
Build and extend the AI registry for models, agents, prompts, tools, and datasets, including owners, versions, and approval state.
Add governance capabilities such as policy checks, guardrails, approval steps, and audit logs.
Write evaluations and regression tests so AI changes are shipped with evidence.
Add tracing, cost and latency dashboards, and quality monitoring.
Build retrieval pipelines using chunking, embeddings, and hybrid search that respect caller permissions, and measure their effectiveness.
Deploy reproducibly into customer AWS environments, including private VPCs, restricted networks, and private endpoints, without manual steps.
Support demos, working sessions, and security reviews with customer engineers.
Own features from design through deployment and operate the systems built.