
Senior Applied ML Engineer
Posted 10 hours ago

Posted 10 hours ago
This is a fully remote position, open to applicants in United States.
• Design and develop the foundational architecture for the memory subsystem, encompassing storage tiers, retrieval pipelines, and privacy-aware filtering.
• Create evaluation frameworks to assess memory retrieval quality, relevance scoring, and effectiveness of augmentation.
• Implement systems for memory extraction and classification to identify, rank, and highlight relevant user contexts from chat histories.
• Conduct research and adapt memory architectures based on academic literature and open-source projects.
• Architect the memory update pipeline utilizing relevance feedback, correction mechanisms, and adaptive privacy classification.
• Design hybrid search strategies that integrate semantic embeddings, structured metadata, graph relationships, and temporal patterns.
• Collaborate with the Product Manager to establish technical constraints and assess feature feasibility.
• Ensure production reliability for AI functionalities and engage in on-call support for prompt failures, extraction issues, and integration disruptions.
• Employ failure-mode and fallback strategies, including graceful degradation, retries, and escalation to human review.
• Act as the founding ML engineer responsible for shaping production memory systems aimed at delivering personalized AI experiences and privacy-aware user context.
• A minimum of 5 years of overall experience, including at least 3 years in software engineering and 2 years focused on building ML/NLP systems.
• Practical experience in developing LLM-powered systems that emphasize context management, memory persistence, or personalization.
• Production experience with vector databases such as Pinecone, Weaviate, or Chroma.
• Familiarity with hybrid searches that combine both semantic and keyword search methodologies.
• Experience in deploying LLM-powered features into production environments.
• A solid understanding of prompt engineering, context window management, and API reliability patterns.
• Hands-on experience with LLM orchestration frameworks such as LangChain, LangGraph, Mem0, MemGPT, or Letta.
• Capability to implement hybrid searches using dense vectors, sparse indices, and metadata filtering.
• Strong debugging abilities for RAG pipelines, prompt reliability, extraction accuracy, and function calling/MCP integrations.
• Experience with agentic architectures, tool calling, MCP, and function orchestration.
• Familiarity with privacy-preserving ML or strict data isolation requirements.
• Proficiency in Python programming.
• Working knowledge of JavaScript/TypeScript for API integration and JSON schema development.
• Understanding of transformer networks and attention mechanisms.
• Experience with graph databases or knowledge graphs.
• Familiarity with testing LLM applications, evaluation datasets, and A/B testing methodologies.
• Experience in designing LLM-friendly APIs with structured outputs, streaming responses, and token optimization.
• Background in experiment tracking and model versioning.
• Knowledge of GDPR/CCPA compliance and data deletion, consent management, or audit trails.
• Experience in recommendation systems or personalization engines.
• Contributions to open-source LLM/RAG projects or research related to memory.
• A Master’s or PhD degree is advantageous but not mandatory.
• Educational qualifications are not a prerequisite for this role.
• Proficiency in Python, FastAPI, Git/GitHub, GitHub Actions, JSON, vector databases, PostgreSQL, MongoDB, LLM orchestration frameworks, and model provider APIs.
• Opportunity to work remotely at a company that embraces a remote-native culture.
• Emphasis on asynchronous communication.
• Commitment to a sustainable performance culture that prioritizes well-being over burnout.
• An equal-opportunity workplace.
• An inclusive and equitable application process.
• Chance to influence AI product development and tackle challenging AI issues.
Entrada
Find Your Talent (FYT)
Inmetrics
SandboxAQ
Get handpicked remote jobs straight to your inbox weekly.