Sr. AI Platform Engineer
About The Position
Ferry International is the #1 real estate coaching company in the world. We help real estate professionals build stronger businesses, create better lives, and achieve measurable results through coaching, training, technology, and community. As AI becomes an increasingly important part of how we serve our clients, we are investing in the infrastructure, data, and technology required to turn promising ideas into reliable products. This is an opportunity to join a team that is building that foundation from the ground up. We’re looking for a Sr. Data Platform Engineer to own the systems underneath and around our AI applications. Our engineering lead owns discovery and agent design. They focus on the business questions, modeling, and orchestration logic. You’ll own everything that makes those systems dependable in production. You’ll build the data pipelines that feed our AI, the retrieval systems that help it access the right information, the AWS infrastructure it runs on, and the memory and evaluation systems that allow it to improve over time. This is a hands on builder role for someone who enjoys taking validated ideas and turning them into reliable, scalable production systems. You’ll have significant ownership and the opportunity to shape the technical foundation behind our next generation of AI products.
Requirements
- 5 to 8 years of relevant engineering, data engineering, infrastructure, or related experience.
- Strong Python and SQL skills with hands on experience building data pipelines using PostgreSQL.
- Experience with vector databases or vector search technologies such as pgvector.
- Strong AWS experience, including services such as ECS, Fargate, RDS, and S3.
- Experience with containers, CI/CD, infrastructure as code, and cloud operations.
- Experience building data infrastructure supporting machine learning or LLM applications.
- Hands on experience with embeddings and retrieval systems.
- Working familiarity with LangGraph or the LangChain ecosystem.
- Experience building observability, monitoring, dashboards, and alerting for production systems.
- Strong understanding of system reliability, scalability, security, and cost management.
- Ability to take validated modeling and transform it into production grade systems.
- Strong communication and collaboration skills.
Nice To Haves
- Experience with Model Context Protocol (MCP) or similar tool calling interfaces.
- Experience with LLM evaluation and observability tools, including LLM as judge systems, tracing, and regression suites.
- Experience with TypeScript and React for internal dashboards or administrative tools.
- Experience working with AI products or agent based applications.
Responsibilities
- Build and maintain production ready data and machine learning pipelines that transform validated modeling into reliable systems.
- Own ingestion, cleaning, embeddings, scoring, and processing across our coaching transcript data.
- Solve the real world data problems that come with a growing system, including mixed storage formats, missing records, historical data, and backfill requirements.
- Own the data corpus and retrieval layer from end to end.
- Modernize embedding infrastructure and consolidate vector storage to improve performance and reliability.
- Ensure retrieval is properly scoped and isolated for each client.
- Own how our AI systems are deployed, operated, monitored, and scaled.
- Build and maintain containerized deployments, CI/CD pipelines, infrastructure as code, environments, observability, alerting, and cost monitoring across AWS.
- Create infrastructure that is reliable, secure, scalable, and cost effective.
- Build the dashboards and monitoring systems that allow the team to understand system performance and identify issues before they become problems.
- Build the durable state, client memory, and retrieval layers that support our AI agent applications.
- Create systems that allow client profiles, commitments, history, and other important information to persist across interactions and over time.
- Make those systems fast, reliable, observable, and scalable.
- Turn established evaluation criteria and benchmark data into automated systems that measure AI performance at scale.
- Build automated evaluations that can run through CI and help determine whether new releases are ready for production.
- Develop regression testing and monitoring processes that help the team identify performance issues and maintain quality as the system evolves.
- Treat client and conversation data as sensitive information.
- Build and maintain appropriate systems for retention, access control, encryption, and data security.
- Develop a clean and reliable process for removing client information when requested.
- Help ensure our AI infrastructure is built with security, privacy, and responsible data management in mind.
Stand Out From the Crowd
Upload your resume and get instant feedback on how well it matches this job.
What This Job Offers
Job Type
Full-time
Career Level
Senior
Education Level
No Education Listed
