Senior AI Engineer - Forward Deployed (FDE)

Moring Ai•Atlanta, GA

1d•Onsite

About The Position

Moring is hiring a Senior AI Engineer for a senior individual-contributor, forward-deployed role. The engineer will apply deep software engineering and cloud-platform expertise alongside recent hands-on AI experience to build reliable, secure, cost-effective AI systems. The role spans shipping AI capabilities in the product and building the platform primitives underneath them, including model access, agent orchestration, retrieval, and evaluation. The engineer will own systems end to end, make architecture decisions, and lead through technical contribution rather than people management. This is a customer-facing role. The engineer will work directly with enterprise customers, embedded with their teams and within their systems, security constraints, and environments. Responsibilities include discovering customer needs, designing and delivering suitable solutions, integrating with enterprise systems, deploying into customer infrastructure, and communicating with technical and business stakeholders. Learnings from customer deployments should inform product and platform improvements. The position is based 100% on-site in Atlanta, Georgia, with travel to customer sites of up to 30%. Applicants must be authorized to work in the United States; visa sponsorship is not available. To apply, send a resume and a short note about an AI agent, application, or system you have built to [email protected].

Requirements

8–12 years of software engineering experience, including significant experience building cloud-native systems, backend services, or platforms; platform engineering background is strongly preferred.
Deep, hands-on AWS expertise, including EKS/ECS, Lambda and serverless patterns, IAM, networking, and infrastructure as code using Terraform or CDK.
Experience operating production services with real SLOs.
Strong Python skills and production engineering practices, including testing, code review, observability, and clean design under deadline pressure.
Solid grounding in distributed systems, API design, and event-driven architecture.
Recent, demonstrable, hands-on 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 or CrewAI, or a comparable framework, and with major model APIs including Anthropic, OpenAI, and Bedrock.
Practical understanding of LLM behavior, including context management, token economics, cost and latency trade-offs, and how non-determinism affects testing and deployment.
Good understanding of RAG, especially retrieval, and how to measure whether retrieval is working.
Familiarity with MCP, including its current limitations and security considerations.
Experience integrating enterprise systems, such as identity and SSO (SAML/OIDC), enterprise APIs, data platforms, or systems of record, and working within enterprise security, network, and compliance constraints.
Customer-facing engineering skills: credibility with client architects and business owners, ability to run demos and discovery sessions, and ability to explain trade-offs plainly.
Authorization to work in the United States; visa sponsorship is not available.

Nice To Haves

Experience building or operating a model or LLM gateway or proxy layer.
Model serving experience, such as vLLM, GPU scheduling, or inference optimization.
Experience with guardrails, prompt-injection defense, or LLM security, including the OWASP LLM Top 10.
TypeScript experience for product-surface work.
Prior startup experience shipping with small teams and moving quickly without breaking trust.
Prior forward-deployed, solutions engineering, or technical consulting experience with enterprise customers.
Experience delivering customer-deployable software, such as single-tenant, customer-VPC, or on-premises models.

Responsibilities

Design, build, and ship agents, agentic workflows, and LLM-powered product features from prototype through production.
Build retrieval systems using chunking and embedding strategies, vector and hybrid search, and re-ranking; measure retrieval quality.
Integrate Anthropic, OpenAI, and Bedrock model APIs, and enable tool and data access through MCP while addressing security considerations.
Conduct technical discovery with customer teams, map their workflows and systems, shape solutions for their environments, and build and ship those solutions.
Integrate with enterprise identity and SSO, APIs, data warehouses, legacy databases, and systems of record such as Salesforce, ServiceNow, or SAP.
Deploy software into customer AWS accounts, private VPCs, and restricted networks, designing for customer security models.
Lead customer working sessions and demos, and participate credibly in enterprise information-security and architecture reviews.
Translate field learnings, integration patterns, platform gaps, and recurring requests into product and platform improvements.
Build a model-access layer that supports multiple providers, routing based on cost, latency, and capability, caching, rate limits, and per-feature cost tracking.
Build agent orchestration and lifecycle capabilities, including state and memory, retries, guardrails, versioning, and rollback.
Create an evaluation harness with automated evaluations and regression tests integrated into CI/CD.
Instrument AI systems with tracing of agent reasoning and tool calls, cost and latency dashboards, and quality monitoring.
Own AWS infrastructure for AI workloads, including EKS/ECS, Lambda, IAM, networking, and infrastructure as code.
Operate production systems, including production ownership, on-call practices, and performance and cost tuning as usage grows.
Drive design reviews, establish technical patterns, make and defend architecture decisions, and mentor one to two engineers.
Make pragmatic build-versus-buy decisions and improve the team's AI engineering practices.