Senior Research Engineer
Own the end-to-end lifecycle of memory features for AI agents. Fine-tune models, implement research, build evaluations, and ship production systems with Engineering.
About the job
What You'll Do
- Fine-tune and train models for memory extraction, updates, consolidation/forgetting, and conflict resolution; iterate based on data and outcomes.
- Read, reproduce, and implement research: quickly prototype paper ideas, benchmark against baselines, and productionize what wins.
- Build evaluation at scale: automated relevance/accuracy/consistency metrics, gold sets, online A/B & interleaving, and clear dashboards.
- Work closely with customers to uncover pain points, turn them into research hypotheses, and validate solutions through field trials.
- Partner with Engineering to ship: design APIs and data contracts, plan safe rollouts, and maintain SOTA latency, reliability, and cost at scale.
Minimum Qualifications
- Experience in RAG or information retrieval (retrieval, ranking, query understanding) for real products.
- Model training/fine-tuning experience (LLMs/encoders) with a strong footing in experimental design and iteration.
- Strong Python; deep experience with PyTorch and familiarity with vLLM and modern serving frameworks.
- Built evaluation for complex language and/or retrieval and generation tasks (gold sets, offline metrics, online tests).
- Able to orchestrate data pipelines to run these models in production with low-latency SLAs (batch + streaming).
- Clear, concise communication with stakeholders (engineering, product, GTM, and customers).
Nice to Have
- Publications at venues like NeurIPS, ICML, ACL, etc.
- Experience with privacy-preserving ML (redaction, differential privacy, data governance).
- Deep familiarity with memory/retrieval literature or prior work on memory systems.
- Expertise with embeddings, vector-DB internals, deduplication, and contradiction detection.
Skills
Python, PyTorch, vLLM, RAG, Information Retrieval, Llm Fine-Tuning, Model Training, Evaluation Metrics, Data Pipelines, Vector Databases
Similar jobs
ML Engineering jobs
Swayable
New York, NYSenior engineer developing and productizing AI, machine learning, scientific computing, and data-analysis capabilities for a high-performance analytics engine. Requires 5+ years building quantitative data-intensive software and expertise in Python, machine learning, scalable architecture, and distributed computing.
PrizePicks
United States
Build and ship production Applied AI capabilities, including agent infrastructure, RAG services, evaluation systems, and AI-powered engineering workflows. The role requires 6+ years of software engineering experience, strong backend and distributed-systems skills, and direct experience delivering LLM- or ML-powered products.
Ai2
Seattle, WA
Senior Research Engineer tailoring and deploying machine learning models for partner applications across geospatial and environmental domains. The role requires PyTorch expertise, end-to-end ML deployment experience, geospatial tools knowledge, and strong independent execution.
Instacart
United StatesBuild and deploy machine learning systems that apply economic theory, econometrics, and causal inference to marketplace problems. The role requires advanced training in economics, strong Python and data skills, and production ML experience for senior-level hires.
Everlaw
Oakland, CA
Builds and operates AI platform capabilities including RAG pipelines, semantic retrieval, agentic orchestration, and LLM integrations to power legal tech products. Requires 4+ years in distributed cloud systems, AI/ML experience, and proficiency in modern programming languages.