The company is building identity trust infrastructure for the digital economy, verifying 100% of legitimate identities in real time and stopping fraud before it starts.
Its work affects businesses, governments and millions of people every day.
The team looks for people who take on high responsibility, move quickly, reason carefully, act like owners and focus on precise solutions to customer problems. The role is not a good fit if you want predictable work or a narrow scope.
This is a hands-on backend engineering role on the backend, AI and machine-learning foundations behind the company's agentic investigation systems.
You will work across backend services, distributed systems, AI agents, retrieval, machine-learning models and production infrastructure.
The systems support multi-step investigations such as watchlist review, sanctions and PEP matching, adverse-media analysis, fraud-ring correlation, case management and other risk and compliance workflows.
A central goal is giving agents accurate, relevant and timely domain knowledge, including contextual information, structured and unstructured data, knowledge-graph retrieval and preserved evidence and provenance.
You will work with senior engineers, machine-learning practitioners, product partners and investigation experts. The role suits an engineer who can own well-scoped features and components, learn fast, contribute to design discussions and grow into broader technical ownership.
Responsibilities
Design, build, test and run backend services for agent orchestration, task execution, state, model integrations and investigation workflows.
Build synchronous and asynchronous agent workflows covering queues, retries, resumability, cancellation, idempotency, scheduling and failure recovery.
Contribute to agent frameworks and developer tooling for tool calling, structured outputs, reusable skills, actor-based workflows, human review and policy-controlled execution.
Build services that inject relevant knowledge into agent workflows based on investigation type, entity, workflow state, customer policy, prior findings and the current task.
Help agents separate authoritative facts, customer-defined policies, derived signals, hypotheses and unverified observations.
Build pipelines that normalize, classify, chunk, index, version and refresh structured and unstructured data, including enrichment.
Implement retrieval using semantic search, lexical search, metadata filters, hybrid retrieval, reranking, entity-aware and temporal filtering.
Contribute to knowledge-graph systems that model entities, relationships, events, evidence, provenance and risk signals.
Support graph traversal, multi-hop retrieval and graph-enhanced context assembly across graph, vector, search, document and API data sources.
Write context-selection logic that balances relevance, freshness, source authority, latency, tenant permissions and model context limits.
Add safeguards that keep stale, contradictory, duplicate, irrelevant, poisoned or unauthorized information out of agent context.
Build short-term task state, investigation history, entity context, retrieval state and provenance for agents.
Connect agents to internal APIs, identity and risk data, case management, watchlists, model endpoints, webhooks and event streams.
Develop secure connector and tool-execution patterns covering authentication, authorization, credentials, tenant isolation, audit logging and sandboxing where appropriate.
Integrate models for classification, ranking, extraction, entity resolution, summarization and other investigation tasks.
Work with ML and data science teammates on features, training data, labeling, dataset quality, model interfaces and deployment.
Contribute to training, fine-tuning and adaptation workflows, including dataset preparation, experiment tracking, evaluation, versioning, deployment and rollback.
Implement model serving and routing that picks models based on task needs, latency, cost, quality, context and data boundaries.
Improve performance through caching, batching, parallel execution, retrieval tuning, context reduction, model selection, prompt tuning and inference configuration.
Build evaluation and regression tests for retrieval quality, grounding, citation accuracy, model behavior, tool selection, workflow completion and end-to-end investigation results.
Write test cases for domain scenarios, ambiguous and adversarial inputs, policy variations, knowledge freshness, retrieval failures and production incidents.
Instrument services with logs, metrics, traces, latency, cost attribution, retrieval diagnostics, model version tracking and dashboards.
Use production telemetry, failed runs, investigator feedback and evaluation results to improve prompts, tools, memory, knowledge sources, models and workflows.
Take part in on-call rotations and incident response for team-owned systems, and help improve monitoring, service-level objectives, capacity planning and recovery procedures.
Write technical designs and implementation notes, take part in code and design reviews, and explain trade-offs clearly.
Work with Product, Fraud and Risk, Investigation Operations, Platform Engineering, SRE, Security, Privacy and Data Science.
Help set engineering standards for testing, observability, deployment, security, maintainability and responsible AI development.
Requirements
Bachelor's or master's degree in computer science, engineering or a related technical field, or equivalent practical experience.
Professional experience building software or backend services, including taking features through testing and production.
Experience with backend development, API design, service-oriented architecture, asynchronous programming, testing, debugging and performance work.
Understanding of distributed-system concepts such as queues, retries, idempotency, timeouts, concurrency, partial failures and reliability.
Experience with a language used for backend or data-heavy systems, such as Python, Java, Go, TypeScript or a comparable language.
Experience building applications on large language models, AI agents, tool calling, retrieval-augmented generation, structured generation or related generative AI.
Understanding of agent architecture, including orchestration, state transitions, task execution, tool use, context management, memory, human escalation and observability.
Experience building backend services, agent components, developer tooling, data pipelines or reusable platform capabilities.
Experience grounding AI or agent workflows in domain knowledge, entity context, customer policies, case history, live data, model outputs or other task-relevant information.
Working knowledge of retrieval concepts such as embeddings, vector search, lexical search, metadata filtering, hybrid retrieval, reranking, query expansion and multi-stage retrieval.
Experience with at least one of: knowledge graphs, graph databases, entity graphs, graph traversal, graph-enhanced retrieval, entity resolution, ontology or schema design, provenance or temporal data modeling.
Experience combining structured data, unstructured documents, search, vector retrieval and live API data sources.
Understanding of context assembly, including relevance, freshness, source authority, permissions, context size, latency and deduplication.
Working knowledge of machine learning, including supervised learning, classification, ranking, embeddings, feature engineering, model evaluation, data quality and model drift.
Experience supporting ML workflows such as dataset preparation, labeling, training, fine-tuning, experiment tracking, evaluation, versioning, deployment or monitoring.
Experience evaluating AI or ML systems with offline datasets, regression tests, production monitoring, task-level metrics or qualitative review.
Experience optimizing AI or ML systems for latency, throughput, cost and quality through caching, batching, parallelism, retrieval tuning, context reduction, model selection or inference configuration.
Experience with cloud infrastructure and containers, preferably AWS and Kubernetes.
Experience with several of: relational databases, queues or event streams, object storage, caching systems, search platforms, vector databases, graph databases and observability platforms.
Understanding of service authentication, authorization, secrets management, tenant isolation, data protection and privacy-sensitive design.
Ability to write maintainable, well-tested code and troubleshoot with logs, metrics, traces, debuggers and other tools.
Ability to break down technical problems, estimate work, identify dependencies, raise risks and deliver features with suitable guidance.
Strong written and verbal communication, and the ability to work well with engineering, product, data science and operations partners.
Startup DNA required: you do well in fast-moving, highly ambiguous settings and take ownership like a founder.
Preferred: experience building AI or ML systems for fraud, identity, financial crime, compliance, trust and safety, investigations or other regulated domains.
Preferred: experience with agent frameworks, model gateways, evaluation and tracing platforms, GraphRAG, enterprise search, MCP-style connectors or custom orchestration.
Preferred: experience with AWS Bedrock, SageMaker, EKS, vLLM, GPU-backed inference or comparable technologies.
Preferred: experience with workflow engines, durable execution, distributed task processing or long-running job orchestration.
Preferred: experience with graph databases or graph processing tools such as Neo4j, Neptune, OpenSearch, Elasticsearch or comparable systems.
Preferred: experience building data enrichment pipelines, entity resolution systems, semantic search, knowledge platforms or retrieval-augmented applications.
Preferred: experience with model monitoring, feature and data drift detection, experiment tracking, model governance or responsible AI practices.
Preferred: experience improving agent and model behavior using traces, evaluation results, investigator feedback, retrieval diagnostics and production failures.
Preferred: experience with fraud, identity, risk, compliance or other high-consequence data.
Preferred: contributions to reusable libraries, technical documentation, testing frameworks, architecture patterns or engineering practices.
Conditions
The company is an equal opportunity employer and does not discriminate on race, religion, color, national origin, gender, sexual orientation, age, marital status, veteran status or disability status.