About this role
Building transformative AI capabilities from the ground up involves designing backend API services, integrating models, and deploying user-facing features that operate in real time. Engineering the data architecture for scalable Generative AI systems requires shaping how information is ingested, transformed, stored, and governed across large enterprise platforms.
Anaplan maintains a leading scenario planning and analysis platform relied upon by thousands of global companies. Joining the team means working at the intersection of artificial intelligence and enterprise software to build retrieval and knowledge layers for agentic workloads and forecasting models.
Successful contributors bring a blend of machine learning foundations and robust data engineering skills. The position suits practitioners who enjoy shipping end-to-end features, optimizing large language models for business planning, and shaping the technical direction of production-grade AI systems.
What you will do
- Contribute to the data 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 optimise LLMs for specific use cases in business planning, including prompt engineering and RAG implementation.
- Design and build the retrieval and knowledge layer powering RAG and agentic workloads, such as vector databases, graph databases, knowledge graphs, hybrid search, and embedding pipelines.
- Build the data plane for evaluation and continuous improvement alongside conversational and agentic AI technologies.
- Engineer feature and context pipelines that feed forecasting and anomaly-detection models at customer scale, balancing batch and streaming patterns.
- Implement evaluation frameworks to measure and improve GenAI feature quality, covering accuracy, latency, and user satisfaction metrics.
What you need
- Demonstrate extensive data engineering experience with a track record of delivering complex projects.
- Showcase hands-on experience building and shipping AI and machine learning products in production environments.
- Apply practical experience with LLM-based systems including RAG architectures, embedding pipelines, prompt logging, and evaluation frameworks.
- Possess hands-on expertise with vector databases, graph databases, and knowledge graphs.
- Bring end-to-end exposure to the model development lifecycle, including training and deploying machine learning models in production.
- Maintain solid knowledge of LLM APIs, prompt engineering, and conversational AI patterns.
- Demonstrate strong expertise in MLOps and LLMOps to ensure scalable, reliable, and monitorable model deployments.
- Display proficiency in Python and modern software development practices such as testing, code review, and CI/CD.
Nice to have
- Hands-on experience with cloud-native ML infrastructure platforms
- Knowledge of vector databases and embedding models
- Experience with model serving frameworks
- Background in forecasting, planning, or analytics applications
- Experience with A/B testing and experimentation frameworks for AI features
Skills and tech stack
Questions candidates ask
What kind of systems and features will I be working on?
You will build user-facing AI features that operate in real time, developing backend API services, model integrations, monitoring, and deployments for GenAI and machine learning systems.
What database technologies and data layers are involved?
The role designs and builds retrieval and knowledge layers for RAG and agentic workloads, utilizing vector databases, graph databases, knowledge graphs, hybrid search, and embedding pipelines.
What programming language and software practices are required?
The position requires proficiency in Python and adherence to modern software development practices including testing, code review, and continuous integration and deployment.
How are job offers handled during the hiring process?
Offers are first extended verbally by a member of the internal recruitment team whenever possible and then followed up via written communication after an extensive interview process with a recruiter and hiring manager.