Sr. Machine Learning Engineer

We are looking for a Senior Machine Learning Engineer to join the Document Product Group and build agentic frameworks from the ground up. You will design the memory and retrieval systems that let agents reason over long horizons, learn from past interactions, and take reliable action. This is a hands-on role for someone who pairs research with the engineering discipline to turn ideas into working systems.

If you want to shape the foundations of how agents remember, retrieve, plan, and act, and you enjoy the ambiguity of 0→1 work, this role is for you.

What You’ll Do

• Design and build agentic frameworks from scratch, including planning, tool use, orchestration, state management, and multi-agent coordination.
• Architect and implement memory systems for agents (short-term, long-term, episodic, and semantic), including write, consolidation, forgetting, and update strategies.
• Build and optimize retrieval systems, including hybrid search, embedding and reranking pipelines, knowledge graphs, and retrieval over structured and unstructured data.
• Turn research ideas and recent literature into rigorous prototypes, then partner with engineering teams to harden them for production.
• Define evaluation methodologies for agent, memory, and retrieval quality, including benchmarks, LLM-as-a-judge approaches, offline and online metrics, and regression testing.
• Build the data pipelines, backend services, and observability needed to operate agentic systems reliably at scale.
• Bring a 0→1 product mindset: shape ambiguous ideas into measurable customer impact, and make informed build-versus-adopt decisions.
• Collaborate with product, design, research, and engineering partners to integrate these capabilities into customer-facing features.
• Stay current with research in agents, memory, retrieval, reasoning, and prompt optimization, and share what you learn with the team.
• Mentor engineers and help raise the team’s technical bar.

What You Need to Succeed

Required Qualifications

• Master’s or Ph.D. in Computer Science, Machine Learning, or a related technical field, or equivalent research experience.
• Research background in areas such as information retrieval, NLP, representation learning, or agents and reasoning, demonstrated through publications, patents, open-source contributions, or equivalent applied research.
• Hands-on experience building memory and retrieval systems for LLM-based applications, going beyond basic RAG to include design tradeoffs, failure modes, and evaluation.
• Demonstrated experience designing and building agentic architectures from first principles (not only configuring existing frameworks), including orchestration, planning, tool use, and multi-agent patterns.
• 10+ years of experience in machine learning engineering, applied research, or production ML systems.
• Strong Python engineering skills, including system design, clean architecture, testing, CI/CD, version control, and code review practices.
• Experience taking ML-powered features from 0→1 through production and ongoing iteration.
• Experience deploying and monitoring ML and GenAI systems in production.
• Strong foundation in classical ML, deep learning, and modern generative AI techniques.
• Solid grounding in data structures, algorithms, and distributed systems.
• Familiarity with cloud platforms (AWS, GCP, or Azure) for scalable deployment.
• Comfort using AI coding agents to accelerate development.
• Excellent written and verbal communication, including the ability to explain complex research to technical and non-technical audiences.

Preferred Qualifications

• Experience with vector databases, graph databases, and search infrastructure
• Experience with long-context strategies, context engineering, memory compression and summarization, and personalization. Contributions to open-source agent, memory, or retrieval projects.
• Experience with prompt optimization frameworks, fine-tuning, and embedding or reranker model training.
• Experience with LLM-as-a-judge, agent evaluation, and benchmark design.
• Experience with MLOps tooling, experiment tracking, model lifecycle management, and observability for LLM and agent workflows.
• Track record of mentoring engineers and influencing technical direction on high-visibility projects.

Expected Pay Range

Our compensation reflects the cost of labor across several U.S. geographic markets, and we pay differently based on those defined markets. The U.S. pay range for this position is $172,500 - $306,625 annually. Pay within this range varies by work location and may also depend on job-related knowledge, skills, and experience. Your recruiter can share more about the specific salary range for the job location during the hiring process. In California, the pay range for this position is $211,800 - $306,625