Foam, part of Whalar Group, is looking to develop advanced AI systems that power their platform, specifically designing and deploying autonomous, stateful AI agents capable of reasoning, learning, and acting in dynamic environments.
Requirements
- 2+ years of experience in machine learning engineering, building production-grade ML systems.
- Hands-on experience with agentic AI frameworks (e.g., LangGraph, LlamaIndex, Zep, Mem0, Langfuse, LangSmith).
- Experience building RAG pipelines, recommendation systems, and/or vector search applications (e.g., Pinecone, Vespa, PostgreSQL + pgvector).
- Strong background in time-series modeling, anomaly detection, and large-scale data analysis (e.g., Clickhouse).
- Skilled in asynchronous API design, containerization, and modern CI/CD workflows (FastAPI, Docker, Kubernetes, GitHub/Bitbucket).
- Excellent EDA skills with the ability to translate data insights into production-ready ML solutions.
- Comfortable working with LLM ambiguity, designing systems that fail gracefully and learn continuously.
Responsibilities
- Design and deploy autonomous AI agents, including reasoning loops, memory layers, and orchestration pipelines.
- Build observability and evaluation systems to monitor reasoning, token usage, and model performance, ensuring reliable production behavior.
- Lead the development of multimodal ML pipelines for semantic search, RAG, recommendation systems, and vector search across text, image, and video data.
- Engineer high-throughput time-series analytics and forecasting models that connect batch OLAP queries with real-time inference.
- Develop and maintain scalable asynchronous APIs and containerized services, ensuring reliability, monitoring, and performance optimization.
- Partner with product and engineering teams to translate business goals into measurable ML outcomes.
- Drive research-to-production pipelines for experimental AI projects and evaluate emerging technologies to advance our platform.
Other
- Proactive, independent, and curious—able to own complex features end-to-end and raise the technical bar for the team.
- Strong communication skills—able to explain trade-offs between AI approaches and align technical metrics to business goals.
- Experience leveraging AI tools and functionality to improve workflow efficiency, research, and experimentation.
- Bachelor's, Master's, or Ph.D. degree in a relevant field (not explicitly mentioned but implied).
- Ability to work in a remote setting and collaborate with teams across different locations.
