Lead development of foundation models, generative AI, and agentic systems for MEP design workflows. Build scalable data pipelines for BIM/CAD and multi-modal geometric datasets, create evaluation and guardrails, translate research into production-grade systems, mentor engineers, and drive technical direction and cross-functional collaboration.
Stratus, deriving from the Latin term meaning 'layer', offers an advanced set of MEP specific solutions that seamlessly layer across a contractor's entire workflow from design to fabrication to installation. Our team of seasoned industry experts, skilled technology leaders, innovators, and entrepreneurs understands that fabrication does not occur in isolation, and increasingly, it may not happen within your own fabrication shop. Through close relationships with our customers—who include some of the most innovative and largest MEP contractors—we have developed a suite of Stratus tools to digitize, automate, and optimize piping, plumbing, sheet metal, and electrical contracting. Stratus provides the software layer an MEP Contractor needs to optimize profits with true "Data Driven Contracting."
GENERAL DESCRIPTION:The Principal AI Engineer builds the agentic intelligence layer for Stratus — the production agent systems, tool integrations, and evaluation infrastructure that let our products reason over MEP fabrication data and act on a contractor's behalf. You will design multi-agent workflows, build the tool and context layer that connects agents to Stratus data, and own the guardrails, evals, and observability that make those systems safe and trustworthy in front of customers.
As a Principal Engineer, you will set technical direction for a small, fast-moving team, mentor engineers, and act as a credible technical voice to executives and customers — translating how these systems work into plain language.
KEY RESPONSIBILITIES:- Design and build agentic workflows: multi-agent orchestration (e.g., LangGraph, CrewAI, AutoGen), tool calling, structured outputs, multi-step planning, and human-in-the-loop checkpoints, to automate complex MEP engineering tasks.
- Establish evaluation, guardrails, and failure-mode analysis for agent systems; including offline eval suites in CI and live production sampling, to ensure they are safe, reliable, and grounded.
- Build the tool and context layer connecting agents to Stratus data via internal and customer-facing APIs (e.g., MCP), including context-window management, permissioning, and cost control.
- Set up observability and tracing for agent behavior; diagnose cost, latency, and hallucination issues in production.
- Integrate Stratus's published design and fabrication data into agent workflows.
- Set technical direction for a small cross-functional team; mentor engineers and drive AI engineering best practices.
- Act as a technical translator to executives and customers — explain agentic systems in plain language and stand behind the workflows you ship.
- Perform requirements analysis with senior stakeholders, ensuring solutions meet immediate product goals and longer-term objectives.
- Contribute to agile workflows, ensuring flexibility and responsiveness to evolving project needs.
- Participate in technical planning and roadmap development.
- 6–8+ years of software engineering experience, with a proven track record of shipping and operating production-grade systems — not just prototypes or notebooks.
- Hands-on experience building and operating agentic systems in production — orchestration frameworks (LangGraph, CrewAI, or AutoGen), tool calling, structured outputs, and eval frameworks.
- Strong computer science fundamentals (data structures, algorithms, system design) and solid API/backend engineering depth.
- Demonstrated ownership of evals, guardrails, and observability for LLM or agent systems.
- Excellent communication skills — able to make complex AI systems legible to executives and customers and to influence technical direction.
- Comfort working in newly forming, ambiguous areas where learning and adaptability are key.
- Degree in Computer Science, Engineering, or a related field, or equivalent practical experience.
- Experience with MCP or similar tool-integration protocols.
- Familiarity working with data derived from CAD/BIM or other 2D/3D model sets.
- Familiarity with machine learning concepts and how data is represented for training.
- Proficiency in C# and strong software development practices.
- Background in customer-facing or professional-services roles.
- Ability to collaborate easily with others and work effectively with minimal direction.
- Drive to continually learn new technologies and seek new ways to solve hard problems.
- Bias toward putting your ideas out there and failing fast.
- Comprehensive and competitive health benefits plan
- Matching 401k contributions
- 20 days annual PTO
- Primarily remote work with occasional annual team onsites.
This is a remote role, but candidates must be based in the U.S.
Similar Jobs
Artificial Intelligence • Big Data • Cloud • Information Technology • Software • Big Data Analytics • Automation
Design and build evaluation and simulation systems for generative AI agents using Dynatrace observability data. Create large-scale simulation pipelines, define metrics/datasets/judging strategies, build developer CLIs, generate adversarial scenarios, and measure agent tool-use and failure modes. Prototype, run feedback cycles, set technical strategy, and mentor engineers.
Top Skills:
Agent FrameworksApmAWSAzureCi/CdCli ToolingDynatraceEvaluation FrameworksGolden DatasetsGCPLlm-As-A-JudgeLlmsObservabilityPairwise ComparisonsPrompt EngineeringTrace Ingestion
Blockchain • eCommerce • Fintech • Payments • Software • Financial Services • Cryptocurrency
Lead design and delivery of production autonomous agents and agentic workflows: architect orchestration, integrate and optimize frontier LLMs, drive model fine-tuning and evaluation, mentor engineers, and translate business goals into safe, reliable, scalable AI-powered product experiences.
Top Skills:
Agent OrchestrationAgentic SystemsFine-TuningLlmsModel DistillationModel OptimizationMulti-Agent CoordinationPrompt EngineeringReinforcement Learning From Human Feedback (Rlhf)Retrieval-Augmented Generation (Rag)
Cloud • Computer Vision • Information Technology • Sales • Security • Cybersecurity
As a Principal Data Engineer, you will design and implement LLM, AI-powered security data platforms, mentor engineers, and drive the adoption of data solutions across teams.
Top Skills:
AirflowAWSBigQueryDaskDockerFlinkGCPKafkaKubeflowKubernetesLangchainLlamaindexMlflowMlops ToolsOciPulsarPythonSagemakerSnowflakeSparkVertex Ai
What you need to know about the NYC Tech Scene
As the undisputed financial capital of the world, New York City is an epicenter of startup funding activity. The city has a thriving fintech scene and is a major player in verticals ranging from AI to biotech, cybersecurity and digital media. It also has universities like NYU, Columbia and Cornell Tech attracting students and researchers from across the globe, providing the ecosystem with a constant influx of world-class talent. And its East Coast location and three international airports make it a perfect spot for European companies establishing a foothold in the United States.
Key Facts About NYC Tech
- Number of Tech Workers: 549,200; 6% of overall workforce (2024 CompTIA survey)
- Major Tech Employers: Capgemini, Bloomberg, IBM, Spotify
- Key Industries: Artificial intelligence, Fintech
- Funding Landscape: $25.5 billion in venture capital funding in 2024 (Pitchbook)
- Notable Investors: Greycroft, Thrive Capital, Union Square Ventures, FirstMark Capital, Tiger Global Management, Tribeca Venture Partners, Insight Partners, Two Sigma Ventures
- Research Centers and Universities: Columbia University, New York University, Fordham University, CUNY, AI Now Institute, Flatiron Institute, C.N. Yang Institute for Theoretical Physics, NASA Space Radiation Laboratory
