
Senior ML Engineer
Posted 21 hours ago

Posted 21 hours ago
This is a fully remote position, open to applicants anywhere in the world.
• Design and develop the essential architecture for memory subsystems, which includes storage layers, retrieval pipelines, and privacy-conscious filtering.
• Create evaluation frameworks to assess memory retrieval quality, relevance scoring, and the effectiveness of augmentations.
• Implement systems for memory extraction and classification to identify, rank, and highlight pertinent user context from chat histories.
• Investigate and modify memory architectures based on academic literature and open-source projects such as MemGPT, Reflexion, and cognitive systems.
• Design the memory update pipeline utilizing relevance feedback, correction methods, and adaptive privacy classification.
• Develop hybrid search strategies that integrate semantic embeddings, structured metadata, graph relationships, and temporal trends.
• Collaborate with the Product Manager to outline technical constraints and assess feature feasibility.
• Take ownership of production reliability for AI features, including providing on-call support for prompt failures, extraction challenges, and integration issues.
• Apply strategies for failure management and fallback, including graceful degradation, retries, and escalation to human review.
• Join as the pioneering ML engineer and influence the development of production AI memory systems.
• Over 5 years of cumulative experience, with a minimum of 3 years in software engineering and 2 years focused on building ML/NLP systems.
• Practical experience in developing LLM-driven systems aimed at context management, memory persistence, or personalization.
• Production-level experience with vector databases such as Pinecone, Weaviate, Chroma, or Qdrant, along with hybrid search systems.
• Proven track record of deploying LLM-based features in production.
• Knowledge of prompt engineering, context window management, and patterns for API reliability.
• Hands-on experience with LLM orchestration frameworks such as LangChain, LangGraph, Mem0, MemGPT, Letta, LlamaIndex, or Haystack.
• Capability to implement hybrid search using dense vectors, sparse indices, and metadata filtering.
• Strong skills in debugging RAG pipelines, prompt reliability, extraction accuracy, and function calling/MCP integrations.
• Familiarity with agentic architectures, tool calling, MCP, and function orchestration.
• Experience with privacy-preserving ML or strict data isolation mandates.
• Proficient in Python programming.
• Basic knowledge of JavaScript/TypeScript for API integration and JSON schema design.
• Familiarity with transformer networks and attention mechanisms.
• Experience with graph databases or knowledge graphs.
• Understanding of testing LLM applications, evaluation datasets, prompt regression tests, and A/B testing.
• Experience in designing LLM-friendly APIs that feature structured outputs, streaming responses, and token optimization.
• Background in experiment tracking and model versioning.
• Knowledge of GDPR/CCPA compliance, including data deletion, consent management, or audit trails.
• Background in recommendation systems or personalization engines.
• Contributions to open-source LLM/RAG projects or research related to memory.
• Proficient in Python, FastAPI, Git/GitHub, GitHub Actions, and JSON.
• Educational qualifications are not a prerequisite for this position.
• Remote-first work environment.
• Flexible communication styles.
• Commitment to a sustainable performance culture that avoids burnout.
• Inclusive and fair hiring practices.
• Equal-opportunity employment.
• Opportunity to tackle challenging AI problems and contribute to the development of AI memory systems.
• Diverse and global team culture.
Memory Bridge
Entrada
Find Your Talent (FYT)
Inmetrics
Get handpicked remote jobs straight to your inbox weekly.