Senior Machine Learning Engineer (Agentic Systems)

Quick Facts

• Build agentic frameworks and core systems for agent memory, retrieval, planning, and action
• Hands-on role blending research and engineering to deliver production-ready capabilities

Description

Build agentic frameworks from scratch, including orchestration, planning, tool use, state management, and multi-agent coordination. Design and optimize agent memory and retrieval systems so agents can reason over long horizons, learn from past interactions, and take reliable action. Convert research into rigorous prototypes and then work with engineering teams to harden and evaluate them for production.

Responsibilities

• Design and build agentic frameworks from first principles (planning, tool use, orchestration, state management, multi-agent coordination)
• Architect memory systems (short-term, long-term, episodic, semantic) including write, consolidation, forgetting, and update strategies
• Build and optimize retrieval systems (hybrid search, embedding and reranking pipelines, knowledge graphs, retrieval over structured/unstructured data)
• Turn research literature into prototypes and partner with engineering teams to productionize
• Define evaluation methodologies for agent, memory, and retrieval quality (benchmarks, LLM-as-a-judge, offline/online metrics, regression testing)
• Create data pipelines, backend services, and observability for reliable operation at scale
• Apply a 0-to-1 mindset to translate ambiguous ideas into measurable customer impact
• Collaborate across product, design, research, and engineering to integrate capabilities into customer-facing features
• Stay current on research in agents, memory, retrieval, reasoning, and prompt optimization
• Mentor engineers and raise the team’s technical bar

Requirements

• Master’s or Ph.D. in Computer Science/ML or related field, or equivalent research experience
• Research background in information retrieval, NLP, representation learning, or agents/reasoning (publications/patents/open-source or equivalent)
• Hands-on experience building LLM memory and retrieval systems beyond basic RAG, including tradeoffs, failure modes, and evaluation
• Experience designing agentic architectures from first principles (orchestration, planning, tool use, multi-agent patterns)
• 10+ years in ML engineering, applied research, or production ML systems
• Strong Python engineering skills (system design, testing, CI/CD, version control, code review)
• Experience moving ML features from 0-to-1 through production iteration
• Experience deploying and monitoring ML/GenAI systems in production
• Strong foundation in classical ML, deep learning, and generative AI
• Grounding in data structures, algorithms, and distributed systems
• Cloud familiarity (AWS/GCP/Azure)
• Comfort using AI coding agents to accelerate development
• Excellent communication for technical and non-technical stakeholders

Benefits

• Competitive compensation (U.S. pay range $172,500–$306,625 annually; California $211,800–$306,625)
• Potential eligibility for long-term incentives in certain roles (e.g., equity awards)