Senior Software Engineer – Backend Platforms and Agentic & ML Systems
Socure · Hub - San Francisco
About this role
## Why Socure Socure is building the identity trust infrastructure for the digital economy—verifying 100% of good identities in real time and stopping fraud before it starts. The mission is big, the problems are complex, and the impact is felt by businesses, governments, and millions of people every day. If you want to help build the future of identity with a team that holds a high bar for itself, keep reading. --- ## Job Overview We’re looking for a **Software Engineer – Backend Platforms and Agentic & ML Systems** to help build the backend, AI, and machine-learning foundations that power Socure’s agentic investigation systems. This is a hands-on role across: - Backend services & distributed systems - AI agents & orchestration - Retrieval (RAG) and knowledge grounding - ML model integration, evaluation, and production operations - Reliable infrastructure for multi-step investigations You’ll design, implement, test, and operate software supporting: - Agent orchestration and asynchronous workflows - Knowledge retrieval and model integration - Evaluation and dependable production operation You’ll contribute to systems supporting investigations such as: - Watchlist review - Sanctions & PEP matching - Adverse-media analysis - Fraud-ring correlation - Case management and other risk/compliance workflows A key part of the role is helping agents use **accurate, relevant, and timely domain knowledge**, including: - Dynamically providing contextual information - Combining structured + unstructured data - Knowledge-graph and retrieval workflows - Preserving evidence and provenance for downstream decisions --- ## Job Responsibilities - Design, implement, test, and operate backend services for agent orchestration, task execution, state management, model integrations, and investigation workflows. - Build synchronous and asynchronous workflows (queues, retries, resumability, cancellation, idempotency, scheduling, failure recovery). - Contribute to agent frameworks and developer harnesses (tool calling, structured outputs, reusable skills, actor-based workflows, human review, policy-controlled execution). - Implement services that inject relevant knowledge into agent workflows based on investigation type, entity context, workflow state, customer policy, prior findings, and task requirements. - Build domain-grounding capabilities to distinguish authoritative facts, policies, derived signals, hypotheses, and unverified observations. - Develop knowledge-ingestion and enrichment pipelines (normalize, classify, chunk, index, version, refresh structured/unstructured data). - Implement retrieval workflows (semantic + lexical search, metadata filtering, hybrid retrieval, reranking, entity-aware retrieval, temporal filtering). - Contribute to knowledge-graph systems (entities, relationships, events, evidence, provenance, risk signals). - Support graph traversal and multi-hop retrieval, and integrate graph/vector/search/document/API sources. - Implement context-selection logic balancing relevance, freshness, source authority, latency, tenant permissions, and model context limits. - Add safeguards against stale, contradictory, duplicated, irrelevant, poisoned, or unauthorized information entering agent contexts. - Build agent state and memory (task state, investigation history, entity context, retrieval state, provenance). - Integrate agents with internal APIs and systems (identity/risk data, case management, watchlists, model endpoints, webhooks, event
Listing freshness
CronJobs last confirmed this listing 2h ago. If its source stops confirming the opening for seven days, this page is removed from active inventory.