Senior Backend Software Engineer (Platforms & Agentic/ML Systems)

Socure

New York, NY • 18m ago • On-site

Senior

On-site

230,000 - 270,000 USD/yr

  1. Select offer
  2. Add resume
  3. Analyze
  4. Improve
  5. Apply
  6. Auto-send · soon

Match your resume with similar open roles

Upload your resume to automatically match with active openings similar to this role.

PDF up to 10 MB

Your resume is private & secure

Resume Checker & Builder preview

Potential salary for Senior Backend Software Engineer (Platforms & Agentic/ML Systems) role

Improve your resume now

$230,000 – $270,000/year

Quick Facts

Role: Senior Backend Software Engineer (Platforms & Agentic/ML Systems)

Focus: Backend platform capabilities for agent orchestration, retrieval/knowledge systems, and production ML operations.

Description

Build and operate backend platform capabilities that power agentic investigation systems, including agent orchestration, asynchronous workflows, knowledge retrieval, and reliable production operations. Implement domain grounding, knowledge ingestion/enrichment pipelines, knowledge-graph and hybrid retrieval, and integrate AI/ML model serving and evaluation. Contribute to systems that support multi-step risk and compliance investigations such as watchlist review, sanctions/PEP matching, adverse-media analysis, fraud-ring correlation, and case management.

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 with queues, retries, resumability, cancellation, idempotency, scheduling, and failure recovery.
  • Contribute to agent frameworks and developer harnesses supporting tool calling, structured outputs, reusable skills, actor-based workflows, human review, and policy-controlled execution.
  • Dynamically inject relevant knowledge into agent workflows based on investigation type, entity context, workflow state, customer policy, prior findings, and current task requirements.
  • Develop knowledge-ingestion and enrichment pipelines and implement hybrid retrieval workflows (semantic/lexical, metadata filtering, reranking, entity-aware retrieval, temporal filtering).
  • Build knowledge-graph systems for entities, relationships, events, evidence, provenance, and risk signals; assemble graph-enhanced context across graph/vector/search/document/API sources.
  • Implement context-selection logic and safeguards to prevent stale/contradictory/duplicated/irrelevant/poisoned/unauthorized information from entering agent contexts.
  • Implement agent state and memory and integrate agents with internal APIs, case-management systems, watchlist systems, model endpoints, webhooks, and event streams.
  • Create secure connector and tool-execution patterns (authentication, authorization, credential management, tenant isolation, audit logging, sandboxed execution).
  • Integrate and optimize ML models for investigation tasks; partner on training/fine-tuning, evaluation, monitoring, and deployment workflows.
  • Improve performance via caching, batching, parallel execution, retrieval optimization, context reduction, model selection, and efficient inference configuration.
  • Develop evaluation and regression tests, add production instrumentation (logs/metrics/traces), and use telemetry and feedback to improve models, prompts/tools, memory, knowledge sources, and workflow design.
  • Participate in on-call, incident response, technical designs, and cross-functional collaboration with product, fraud/risk, investigation operations, platform/SRE, security/privacy, and data science.

Requirements

  • Bachelor’s or master’s degree in Computer Science/Engineering (or equivalent practical experience).
  • Experience building backend services end-to-end, from implementation through testing and production operation.
  • Backend/API/service-oriented architecture experience; strong asynchronous programming/testing/debugging/performance skills.
  • Distributed systems fundamentals (queues, retries, idempotency, timeouts, concurrency, partial failures, reliability).
  • Programming language for backend/data-intensive systems (Python, Java, Go, TypeScript, or comparable).
  • Experience with LLMs/AI agents, tool calling, RAG, and/or structured generation.
  • Knowledge of agent architecture: orchestration, state transitions, tool use, context management, memory, human escalation, observability.
  • Practical retrieval experience: embeddings/vector search, lexical search, metadata filtering, hybrid retrieval, reranking, query expansion, multi-stage retrieval.
  • Experience with knowledge graphs/graph databases and related concepts (entity graphs, traversal, entity resolution, provenance/temporal modeling, ontology/schema).
  • Ability to combine structured data, unstructured documents, search/vector retrieval, and live API data sources.
  • Understanding of context assembly/prompt-context construction (relevance, freshness, authority, permissions, context size, latency, deduplication).
  • Machine-learning knowledge and ML workflow experience (classification/ranking/embeddings, feature engineering, evaluation, drift; dataset prep/labeling/training/fine-tuning, experiment tracking, versioning, deployment, monitoring).
  • Experience evaluating AI/ML systems using offline datasets, regression tests, production monitoring, and/or qualitative review.
  • Experience optimizing AI/ML for latency/throughput/cost/quality and deploying on cloud/container infrastructure (preferably AWS and Kubernetes).
  • Security understanding for service authn/authz, secrets management, tenant isolation, and privacy-sensitive design.
  • Maintainable, well-tested coding and troubleshooting using logs/metrics/traces and debugging tools.
  • Strong communication and the ability to scope work, estimate effort, identify dependencies/risks, and deliver.

Benefits

  • High-ownership backend role building reliable platforms for agentic investigations.
  • Opportunity to work across backend systems, distributed orchestration, retrieval/knowledge systems, and applied ML in production.

See similar jobs

Explore similar jobs and use your resume score to choose where to apply next

See more

Unlock Full Resume Report