AI Engineer

*Atlanta, GA (On-Site)*

About the Company:

Moring AI is an applied AI company built to deliver measurable enterprise outcomes. We design, build, and operate production-grade agentic AI applications for Fortune 500 companies and high-growth startups, working across high-complexity domains including finance and insurance claims, healthcare authorizations, enterprise operations, and production SRE. What sets us apart is our proprietary Agentic AI Platform, which we bring to every client engagement, enabling faster delivery, proven architecture, and systems built to run reliably in production from day one. We do one thing well: production-grade agentic AI for enterprises. Every tool, framework, and platform component we have built is purpose-built for that. We own delivery end to end, from understanding the business problem through to production, and we measure success by outcomes, not deliverables. We are based in Atlanta, GA and Chennai, India

What you will do

We are looking for super-talented AI engineers who can design and ship production-grade agentic AI solutions for enterprise clients. You will be part of a lean, fast-moving engineering team with offices in Atlanta, GA and Chennai, India. This is an in-office role; we are not considering remote candidates.

• Design and build agentic AI applications that automate enterprise business workflows end-to-end, covering requirements gathering, agent design,RAG implementation, evaluation, deployment, and post-production monitoring.
• Architect and implement RAG pipelines for enterprise knowledge bases: ingestion, chunking, embedding, hybrid retrieval, re-ranking, and grounded generation optimized for domain-specific accuracy.
• Build multi-agent systems using LangGraph, AutoGen, or equivalent frameworks, including multi-agent orchestration, state management, memory systems, and human-in-the-loop approval flows.
• Integrate and manage LLM APIs across providers (OpenAI, Anthropic, AWS Bedrock, Azure OpenAI, Google Vertex AI), with model selection logic, prompt caching, cost optimization, and failover strategies for production workloads.
• Contribute to the Moring Agentic AI Platform: the AI runtime, AI gateway, agent execution sandbox, and the evaluation and observability suite that all client deployments run on.
• Build and maintain the agent observability stack: tracing, latency instrumentation, hallucination detection, and automated evaluation pipelines (LLM-as-a-judge, regression testing, A/B testing for prompts and model versions).
• Deploy and operate AI infrastructure on cloud platforms (AWS, Azure, GCP) using infrastructure-as-code, Kubernetes, and CI/CD pipelines; provide production support including debugging non-deterministic failures and prompt-level root cause analysis.

What we are looking for

• Professional engineering experience focused on LLM, GenAI, and agentic systems in a production context.
• Proficiency in at least one major agent framework, preferably LangGraph, with hands-on experience implementing multi-agent orchestration, state management, and memory systems for enterprise-grade workflows.
• Deep experience with RAG pipeline design: ingestion strategy, chunking, embedding model selection, vector database integration (Pinecone, Weaviate, Qdrant, ChromaDB, or Milvus), hybrid search, metadata filtering, and retrieval re-ranking to maximize precision in domain-specific contexts.
• Hands-on experience designing and running agent evaluation pipelines in production. You should be able to describe specific eval systems you built, the failure modes they caught, and how they drove improvements. This includes curating evaluation datasets from production traffic, building golden reference sets with domain experts, and managing eval dataset versioning.
• Strong Python fundamentals. You will be writing Python daily, using Claude Code and AI-assisted tooling extensively, and must be able to understand, review, debug, and extend generated code with confidence.
• Advanced prompt engineering: chain-of-thought, few-shot, prompt chaining, and prompt caching optimization for high-volume production workloads.
• Experience integrating multiple LLM providers (OpenAI, Anthropic, AWS Bedrock, Azure OpenAI, Vertex AI) with model selection logic, cost-quality tradeoff analysis, and failover strategies.
• Familiarity with Model Context Protocol (MCP) for standardized agent-to-tool connectivity and runtime tool discovery.
• Proficiency with evaluation frameworks (LangSmith, DeepEval, Langfuse, Braintrust, or OpenAI Evals) and a strong grasp of eval metrics including accuracy, faithfulness, hallucination detection, groundedness, and latency. Experience with LLM-as-a-judge design: writing graded rubrics, calibrating judge models, and building automated evaluation pipelines.
• Regression testing and A/B testing for prompts and model versions, with the ability to define SLOs for agentic systems, detect degradation in production, and trace failures to root cause whether that is a retrieval gap, a model behavior change, or a prompt regression.

**What We Offer
**

• Competitive base salary: $90,000 – $125,000 depending on skills and experience.
• Equity Plan — we want you to share in Moring AI’s success, not just draw a paycheck.
• Comprehensive health, dental, and vision insurance.
• Performance bonus aligned to individual and company outcomes.
• Flexible working hours.
• Hardware stipend: your choice of MacBook Pro or equivalent.
• Annual learning & conference budget to stay at the frontier of AI.
• Opportunity to embed with Fortune 500 clients and solve high-stakes, real-world AI challenges.
• Work alongside a lean, elite team — every engineer here has meaningful impact from day one.

*We don’t just build AI — we deploy it where it matters, with engineers who stay until it works.*

Apply at moring.ai/careers or reach out directly at careers@moring.ai