Principal Engineer (A.I)

Anaplan; New York (NY); On-site; USD 190,000 - 230,000; Full time

Job summary

Anaplan seeks a Principal Engineer, AI to drive GenAI capabilities across the full stack, from model integration to intuitive interfaces. You will lead architecture and deployment of scalable AI systems, ensuring production-grade performance, monitoring, and cost optimization within Anaplan’s planning workflows.

You will collaborate with data scientists to productionize ML models and forecasting algorithms, emphasizing prompt engineering, RAG, and robust observability, with a strong emphasis on

Qualifications

• Advanced degree in CS/AI/ML or related quantitative field.
• Experience with cloud-native ML infrastructure platforms.
• Experience with model observability tools (LangSmith, W&B, MLflow).

Responsibilities

• Lead architecture, design, and deployment of GenAI and ML systems.
• Develop end-to-end GenAI features including APIs, model integration, monitoring, and deployments.
• Integrate and optimize LLMs for enterprise planning use cases, including prompt engineering and RAG.

Skills

MLOps

LLMOps

Python

Prompt engineering

RAG implementation

LLM APIs

Model serving

CI/CD

AB testing

Observability tools

Education

Master's or PhD in CS/AI/ML

Tools

vLLM

TensorRT

Ray

Pinecone

Weaviate

Qdrant

LangSmith

W&B

MLflow

Job description

• We're seeking a Principal Engineer, AI who can work across the full stack of Anaplan AI applications, from model integration and prompt engineering to building intuitive user interfaces
• You'll build production-ready AI features that empower business users to leverage the power of GenAI within their planning workflows, requiring both deep ML knowledge and strong software engineering skills
• Lead the architecture, design, and deployment of scalable Generative AI and Machine learning systems into production environments
• Develop end-to-end GenAI features, including backend API services, model integration, model monitoring, evaluations, and deployments
• Integrate and optimize LLMs for specific business planning use cases, including prompt engineering and RAG implementation
• Build conversational interfaces and agentic workflows that make complex planning tasks accessible through natural language
• Implement evaluation frameworks to measure and improve GenAI feature quality, including accuracy, latency, and user satisfaction metrics
• Design and develop APIs that expose AI capabilities to Anaplan's platform and third-party integrations
• Optimize model inference pipelines for performance, cost, and scalability in production environments
• Implement monitoring, logging, and observability for GenAI systems to track usage, errors, and model behavior
• Collaborate with data scientists to productionise ML models and forecasting algorithms

Strong expertise in MLOps and LLMOps, ensuring scalable, reliable, and monitorable model deploymentsExperience in fine-tuning LLMs for domain-specific enterprise applicationsEnd-to-end exposure in model lifecycle development, including extensive experience in training and deploying ML models in production environmentsProven track record of delivering complex technical projects on time with high qualityProficiency in Python and modern software development practices (testing, code review, CI/CD)Deep knowledge of LLM APIs, prompt engineering, and conversational AI patternsExperience with agentic frameworks and autonomous agent architecturesExtensive hands-on professional experience in the field of Artificial Intelligence, Machine Learning, or related engineering domainsAdvanced degree (Master's or Ph.D.) in Computer Science, Artificial Intelligence, Machine Learning, or a strongly related quantitative fieldHands-on experience with cloud-native ML infrastructure platformsKnowledge of vector databases (Pinecone, Weaviate, Qdrant) and embedding modelsExperience with model serving frameworks (vLLM, TensorRT, Ray)Experience with A/B testing and experimentation frameworks for AI featuresContributions to open-source ML projects or research publicationsExperience with model observability tools (LangSmith, W&B, MLflow)