Leads the team you would join
Leads the work day to day
Owns the opening
From your own Gmail and LinkedIn.
About the role
This is a senior backend and AI platform engineering role at Socure, based in the San Francisco hub and listed as remote. The engineer builds backend services, retrieval systems and agent infrastructure that support investigation workflows such as sanctions screening and fraud-ring correlation. The role suits engineers comfortable with distributed systems, LLM-based agents and production operation.
What you’ll do
- Design, build, test and run backend services for agent orchestration, task execution, state and model integration.
- Build synchronous and asynchronous agent workflows with queues, retries, resumability, cancellation and idempotency.
- Contribute to agent frameworks covering tool calling, structured outputs, human review and policy-controlled execution.
- Inject relevant domain knowledge into agent workflows based on investigation type, entity context and policy.
- Help agents separate authoritative facts from derived signals, hypotheses and unverified observations.
- Build knowledge ingestion and enrichment pipelines that normalise, chunk, index and version data.
- Implement retrieval using semantic, lexical, hybrid and entity-aware methods with reranking.
- Contribute to knowledge-graph systems that represent entities, relationships, evidence and provenance.
- Integrate agents with internal APIs, risk data sources, case management and watchlist systems.
- Build secure connector and tool-execution patterns with authentication, tenant isolation and audit logging.
- Work with data science teams on model training, evaluation, versioning and deployment.
- Build evaluation and regression tests for retrieval quality, grounding, tool selection and investigation outcomes.
What they’re looking for
- A bachelor's or master's degree in Computer Science, Engineering or a related field, or equivalent practical experience.
- Professional experience building backend services and taking features through to production.
- Experience with API design, service-oriented architecture, asynchronous programming and performance work.
- Understanding of distributed-system concepts such as queues, retries, idempotency, timeouts and partial failures.
- Proficiency in a backend language such as Python, Java, Go or TypeScript.
- Experience building applications with LLMs, AI agents, tool calling or retrieval-augmented generation.
- Understanding of agent architecture, including orchestration, state, memory and human escalation.
- Experience grounding AI workflows with domain knowledge, customer policies and live data.
- Practical knowledge of embeddings, vector search, lexical search, hybrid retrieval and reranking.
- Experience with knowledge graphs, entity resolution, ontology design or provenance, in at least one of these areas.
- Experience with AWS and Kubernetes, preferably.
- Understanding of authentication, authorisation, secrets management and tenant isolation.
Nice to have
- Experience building AI or ML systems for fraud, identity, financial crime, compliance or other regulated domains.
- Experience with agent frameworks, model gateways, evaluation platforms, GraphRAG or MCP-style connectors.
- Experience with AWS Bedrock, SageMaker, EKS, vLLM or GPU-backed inference.
- Experience deploying fine-tuned or domain-specific models alongside managed models.
- Experience with workflow engines, durable execution or long-running job orchestration.
- Experience with graph databases such as Neo4j, Neptune, OpenSearch or Elasticsearch.
- Experience with entity-resolution systems, semantic search or retrieval-augmented applications.
- Experience with model monitoring, drift detection or responsible AI practices.
What’s on offer
- Listed as remote, with a San Francisco hub location.
Skills
Questions about this role
Is this role remote?
The listing is marked remote, with a San Francisco hub location.
Do I need a degree?
A bachelor's or master's degree in a technical field is required, or equivalent practical experience.
Which programming languages are needed?
Experience with a backend language such as Python, Java, Go, TypeScript or a comparable language is required.