Provenance Research Jobs (NOW HIRING)

The role focuses on researching, designing, and implementing advanced machine learning systems that improve the portability, reliability, and adaptability of AI agents across diverse environments. You will contribute to applied AI research by building prototypes, evaluation frameworks, and production-ready components that enable intelligent systems to evolve safely and efficiently.

• Design, implement, train, and evaluate machine learning models, routing systems, and AI agent architectures.
• Develop portable abstractions across models, providers, protocols, tools, and agent execution environments.
• Build systems for model routing, quality-cost-latency optimization, and intelligent decision-making.
• Create evaluation frameworks and benchmarks to measure AI system quality, reliability, safety, and portability.
• Develop scalable solutions for memory, context management, retrieval, provenance, and user-controlled AI experiences.
• Define schemas, interfaces, and standards for agent capabilities, tools, actions, skills, and communication protocols.
• Research and prototype agent interoperability solutions, including tool execution and multi-agent workflows.
• Investigate optimization techniques such as distillation, skill generation, reinforcement learning, and automated improvement strategies.
• Build robust research software, APIs, integration layers, and testing infrastructure to support rapid experimentation.
• Collaborate with research, engineering, security, and product teams to transform experimental ideas into reliable AI systems.
• Communicate findings through technical documentation, demonstrations, benchmarks, open-source contributions, and research publications.

The ideal candidate brings deep expertise in machine learning, AI systems, and software engineering, with experience designing and evaluating modern AI applications. You should be comfortable working on complex research problems, developing scalable solutions, and collaborating across technical disciplines.

• Strong understanding of machine learning, large language models, statistical decision-making, or related AI fields.
• Deep expertise in areas such as model routing, AI agents, retrieval systems, memory architectures, evaluation frameworks, distributed systems, or API and protocol design.
• Experience building and evaluating modern language-model or agent-based systems, including multi-turn workflows and tool usage.
• Proven ability to design, execute, and analyze machine learning experiments with strong statistical methodology.
• Experience formulating research questions, testing hypotheses, and deriving reliable conclusions.
• Knowledge of evaluation methodologies, reproducibility, uncertainty estimation, generalization, and avoiding evaluation leakage.
• Strong Python programming skills with excellent software engineering and algorithm design abilities.
• Experience working with APIs, distributed services, data schemas, testing, observability, version control, and CI/CD practices.
• Ability to reason about security, privacy, permissions, provenance, and reliability in AI systems.
• Experience rapidly iterating across models, data, infrastructure, and evaluation approaches.
• Strong communication skills with the ability to document technical work and collaborate with research and engineering teams.
• Excellent English proficiency, including technical writing and presentation skills.

Nice to have:

• Experience with model routers, cascades, mixture-of-experts systems, recommenders, or cost-aware inference.
• Experience integrating multiple AI providers, inference platforms, or open-source model-serving systems.
• Familiarity with AI agent frameworks, coding agents, function calling, MCP, or agent-to-agent communication protocols.
• Experience with retrieval systems, vector databases, knowledge graphs, or advanced context management.
• Knowledge of reinforcement learning, preference learning, reward modeling, or teacher-student distillation.
• Experience with TypeScript, Go, Rust, or other systems programming languages.
• Experience building secure AI systems involving authentication, sandboxing, telemetry, or policy enforcement.
• Experience developing distributed data-processing, evaluation, training, or inference platforms.
• PhD in Computer Science, Artificial Intelligence, Machine Learning, or a related technical field, or equivalent practical experience.
• Track record of impactful publications, open-source projects, or deployed AI systems.

• Competitive compensation package.
• Career growth opportunities and continuous learning support.
• Flexible working environment with strong ownership and autonomy.
• Opportunity to work on impactful AI research and engineering projects.
• Collaborative culture with talented international teams.
• Chance to contribute to the development of future AI technologies.
• Inclusive workplace focused on innovation, trust, and meaningful impact.