Senior Applied Scientist, Organizational Memory (PhD Required)

Job description

Office Location: Wellesley, MA (3 days per week in the office) Company Overview Accrete is an agentic managed services company: we deliver the AI infrastructure and the AI workforce that does high-stakes, judgement-heavy work for government and enterprise clients — at the economics of software, not labor. At the core is Accrete’s Knowledge Engine, a dynamic context graph that captures an organization’s tacit knowledge, resolves data across silos, and builds a living, auditable ground truth. Expert agents reason against that ground truth to act on complex, high-stakes decisions — not just answer questions about them. From national security to commercial operations, Accrete delivers the work on one platform, with unlimited expert agents and expert judgement. Job Description We are looking for a Senior Applied Scientist to contribute to the research and development behind Accrete's context graphs — the intelligence layer the Knowledge Engine and its agents are built on. The work draws on knowledge representation, graph-based machine learning and information retrieval, combined with LLMs , to continuously construct, enrich, reason over, and maintain a structured picture of how an organization operates. Agentic systems are key: the graph and the agent topology built on top of it are designed together, since what agents need to retrieve and act on shapes how the graph is structured. The central challenge is to move past static knowledge graphs and conventional retrieval toward dynamic context graphs that capture how decisions get made and why — the actors, events, risks, and rules involved, the dependencies among them, and how all of it shifts over time. Much of what matters was never written down directly; it has to be reconstructed from the traces work leaves in tickets, threads, and meetings. In practice that means extraction from large volumes of heterogeneous data, resolving entities and relationships across sources, modeling provenance and uncertainty explicitly, and building graph structures agents can reason over reliably. This is an applied research role. Ideas become systems that run on real data at scale, developed alongside engineers and product teams. It also means taking evaluation seriously: there is no easy ground truth for whether a graph captured the right reasoning, and designing the benchmarks and adjudication methods that answer that question is part of the work, not an afterthought. Key Responsibilities Conduct applied research focused on context graphs, knowledge representation, graph intelligence, and AI systems operating over complex, heterogeneous data. Develop algorithms and architectures for constructing and continuously updating dynamic context graphs from structured and unstructured data. Research methods for entity resolution, relationship extraction, event extraction, temporal reasoning, semantic linking, and knowledge discovery across disparate information sources. Develop graph-based representations of entities, relationships, events, decisions, processes, and organizational knowledge. Explore approaches for incorporating time, provenance, confidence, uncertainty, and source attribution into graph-based representations. Develop graph-based methods for supporting LLM reasoning, retrieval, planning, and agentic workflows. Research techniques for combining LLMs with structured graph representations to improve reasoning accuracy, grounding, and explainability. Design and evaluate graph algorithms, embeddings, retrieval methods, and machine learning approaches for discovering latent relationships and relevant context. Investigate methods for identifying changes, inconsistencies, gaps, and emerging patterns within evolving knowledge and context graphs. Develop prototypes and experimental systems and work with engineering teams to translate successful research into scalable production capabilities. Design benchmarks and evaluation frameworks for measuring graph quality, retrieval performance, reasoning accuracy, grounding, and system reliability. Stay current with advances in knowledge representation, graph ML, LLMs, information retrieval, databases, and related research areas. Contribute to technical strategy through research publications, patents, intellectual property, technical documentation, and mentorship. Required Qualifications Ph.D. in Computer Science, Electrical and Computer Engineering, Computational Linguistics, Cognitive Science, or a related technical field, with a research focus in machine learning, NLP, knowledge representation, graph learning, or information retrieval. Research depth in at least two of the following, with working familiarity across the rest: knowledge representation and knowledge graphs; graph-based machine learning; information extraction and NLP; information retrieval and semantic search. A record of peer-reviewed publications at leading venues such as NeurIPS, ICML, ICLR, ACL, EMNLP, KDD, WWW, or ISWC. Experience building extraction pipelines over unstructured and heterogeneous sources — entities, relationships, and events — including LLM-based extraction, retrieval-augmented generation, and embedding methods. Experience designing evaluation for problems without clean ground truth: benchmark construction, human annotation and adjudication protocols, agreement measurement, and baselines strong enough that beating them is meaningful. Strong programming and system-building skills in Python and PyTorch, with hands-on experience using graph databases such as Neo4j and graph learning frameworks such as PyTorch Geometric or DGL. Demonstrated ability to turn research ideas into working systems — research code others can run, open-source contributions, or systems that outlived a single paper's experiments. Ability to formulate research questions independently under ambiguity, and to communicate technical work clearly to research, engineering, and product audiences. Preferred Qualifications Familiarity with cognitive or organizational memory theory (episodic/semantic memory, consolidation, transactive memory, tacit knowledge) and interest in translating it into computational representations of how organizations retain and lose knowledge. Prior industry research internships or post-doctoral experience, particularly applied work on real data at scale. Experience with multi-agent systems built over structured knowledge: agent topology and orchestration, tool interface design, and evaluation of agent trajectories. Experience with dynamic or temporal knowledge graphs, and with temporal graph learning architectures. Experience with schema and ontology evolution in knowledge systems — versioning, migration, and re-extraction as representations change. Experience with belief revision and knowledge maintenance: handling contradictory evidence, retiring stale assertions, and modeling when something was true separately from when the system learned it. Experience adapting or distilling open-weight models to encode domain knowledge, including fine-tuning and knowledge distillation. Experience applying research in enterprise, intelligence, or defense settings, where outputs must be grounded, attributable, and correctable. Salary Range: $160k-$210k The salary range provided reflects the estimated compensation for this role based on the expected qualifications and experience level. The final offer may vary depending on factors such as skills, experience, and alignment with role requirements. Core Values & Expectations: Impact. You take full ownership and accountability for your work, consistently seeing projects through from inception to completion with a strong bias for action. Proactively identifying challenges, you drive solutions rather than waiting for direction, and hold yourself and others to the highest standards for delivering results. With strategic thinking and a problem-solving mindset, you make informed decisions leveraging data and expertise, always looking for ways to improve processes, optimize workflows, and enhance outcomes beyond your immediate responsibilities. Collaboration. You work seamlessly across teams, prioritizing shared goals and team success over individual credit. Engaged listening and open, candid communication are at the heart of your approach, ensuring alignment and synergy throughout the organization. You value diverse perspectives, seeking input from others to drive better results. By treating colleagues with respect and professionalism, you help build a culture of trust, supporting each other through challenges, celebrating successes, and constructively addressing conflicts to strengthen relationships and improve outcomes. Passion for AI & Innovation. You are deeply excited about the transformative potential of AI and committed to contributing to a company shaping the future of work. With curiosity and a growth mindset, you continuously seek to learn, adapt, and stay at the forefront of new developments. Your enthusiasm for innovation drives you to explore new ideas, challenge the status quo, and find creative solutions that deliver meaningful impact. You approach your work with energy and a desire to advance both technology and the way we work. Company Benefits Competitive Salary: Aligned with experience and market standards Comprehensive Insurance: Health, dental, and vision coverage for you and your family 401(k) Plan: Build your financial future with our retirement savings plan Flexible PTO & Hybrid Work: Take time off when needed and enjoy remote flexibility per company guidelines Growth & Development: Access professional learning opportunities and career advancement support Onsite Perks: Enjoy catered lunches, snacks, and a fully stocked kitchen Team Bonding: Company-sponsored happy hours and social events to connect and unwind Accrete is an equal opportunity/affirmative action employer. All qualified applicants will receive consideration for employment without regard to sex, gender identity, sexual orientation, race, color, religion, national origin, disability, protected Veteran status, age, or any other characteristic protected by law.