Production AI Systems Engineer for LLM Pipelines

LandingAI, Inc.; United States; On-site; USD 120,000 - 200,000; Full time

Job summary

Haven Safety is seeking an experienced AI/ML engineer to build and operate the LLM engine that connects evidence bases and knowledge graphs to enterprise investigations. You will report to the CTO and shape the AI roadmap while ensuring precision, traceability, and human oversight in safety-critical deployments.

You will own multi-step reasoning pipelines, grounding, retrieval, evaluation, and production operations across OpenAI, Anthropic, and Google models, with a focus on enterprise customers

Qualifications

• Production LLM systems experience with shipping user-facing features.
• Experience building multi-step tool-calling workflows.
• Structured evaluation with datasets, regression tests, or human review.
• Ability to design context and retrieval strategies for LLMs.
• Ownership from deployment to monitoring and incident response.
• Ability to discuss model tradeoffs across quality, latency, cost.

Responsibilities

• Build and operate multi-step LLM pipelines coordinating model calls, tool calls, graph queries, retrieval, gates, and agent handoffs.
• Extend and orchestrate a team of agents through incident analysis and enterprise learning.
• Design grounding and retrieval across graph traversal and vector search so models see the right evidence.
• Create evaluation datasets, scoring, and per-stage quality attribution for extraction and reasoning tasks.
• Implement production AI operations: tracing, audits, cost/latency monitoring, failure handling, dashboards.

Skills

Production LLM systems

LangGraph

LangChain

Python

Graph reasoning

Education

BS in CS or related field

Tools

Neo4j

Cypher

Azure

Azure Search

Pinecone

MongoDB Atlas

Elasticsearch

Job description

Haven Safety is seeking an experienced AI/ML engineer to build and operate the LLM engine that connects evidence bases and knowledge graphs to enterprise investigations. You will report to the CTO and shape the AI roadmap while ensuring precision, traceability, and human oversight in safety-critical deployments.

You will own multi-step reasoning pipelines, grounding, retrieval, evaluation, and production operations across OpenAI, Anthropic, and Google models, with a focus on enterprise customers