This position requires an ACTIVE SECRET security clearance. Your application will not be reviewed if you do not have an ACTIVE security clearance at SECRET or above.
We are seeking a Senior Agentic AI Engineer to lead the technical design, prototyping, and deployment of autonomous and semi-autonomous AI workflows supporting a federal financial crimes focused agency. In this high-impact role, you will be instrumental in executing an agentic foundation initiative, transitioning the client from productivity tools into an autonomous, ontology-driven fraud detection and targeting ecosystem. Working on a modern AWS GovCloud or Databricks Lakehouse foundation, you will architect multi-agent systems that autonomously triage, auto-tag, and analyze Bank Secrecy Act (BSA) data and Suspicious Activity Reports (SARs). You will implement advanced agentic patterns-such as ontology traversal, entity resolution, iterative hypothesis generation, and tool use-to reduce analyst investigation cycles from weeks and months down to hours and days.
Responsibilities and Duties 1. Agentic Architecture & Orchestration - Architect and scale multi-agent systems driving the agentic foundation, including autonomous agent task routing, iterative planning, reflection, and human-in-the-loop validation.
- Develop specialized agents capable of parsing complex unstructured narratives in SARs, extracting key entities, and applying structured fraud ontologies for automated tagging.
- Implement agent coordination pipelines using frameworks such as LangGraph, AutoGen, CrewAI, or Amazon Bedrock Agents with deterministic fallback logic and schema enforcement.
2. BSA & SAR Fraud Targeting Integration - Bridge agent reasoning with the client's Lakehouse data platform, designing tools and APIs for agents to interrogate high-volume BSA datasets, target data selection notebooks, and risk-ranking pipelines.
- Integrate graph-based ontologies and entity resolution services into reasoning workflows to trace illicit financial networks, anomalous filers, and typologies across BSA filings.
- Support downstream analytic applications including accelerating Foreign Target Assessments (FTAs), Section 311 actions, open request letters, and regulatory comment review.
3. Secure AWS Cloud & Lakehouse Deployment - Deploy production agentic solutions on AWS GovCloud, orchestrating foundation models via Amazon Bedrock.
- Collaborate with data engineering teams to query and interface with Databricks Lakehouse / Delta tables hosting BSA and SPCL data under active Authority to Operate (ATO) guidelines.
- Implement Infrastructure as Code (Terraform or AWS CloudFormation/CDK) and ensure strict compliance with federal zero-trust, RBAC/ABAC, and FedRAMP High security baselines.
4. SI O&M, Model Evaluation, & Guardrails - Design systematic evaluation benchmarks to monitor agent tool-selection accuracy, hallucination rates, and ontology alignment.
- Support ongoing SI Operations & Maintenance (O&M) by calibrating guardrails, managing model risk management (MRM) documentation, and evaluating new foundation model releases.
Required Experience, Skills and Qualifications - Active U.S. Government Secret clearance (with ability to obtain and maintain agency suitability/security vetting).
- 5+ years of software engineering experience with deep expertise in Python.
- 2+ years of hands-on experience designing and operationalizing Generative AI and LLM solutions.
- Demonstrated experience implementing agentic workflows (e.g., tool/function calling, memory management, multi-agent coordination with LangGraph, AutoGen, CrewAI, or Bedrock Agents).
- Experience in AWS environments (Bedrock, SageMaker, OpenSearch, Lambda, Step Functions, S3, IAM).
- Experience working with structured vector databases and semantic search pipelines over large unstructured narrative collections.
- Ability to work East Coast hours
- Ability to work hybrid in Vienna, VA, or remotely
Preferred Qualifications - Financial Crimes Domain: Direct experience working with Bank Secrecy Act (BSA) data, Suspicious Activity Reports (SARs), Anti-Money Laundering (AML), Counter-Terrorist Financing (CTF), or federal fraud analytics.
- Ontologies & Entity Resolution: Hands-on experience integrating knowledge graphs, semantic ontologies, or entity resolution algorithms (e.g., Senzing, Neo4j, Amazon Neptune) into LLM reasoning loops.
- Lakehouse Integration: Familiarity with Databricks, Apache Spark, Delta Lake, or lakehouse architectures deployed within federal cloud environments.
- Federal Compliance: Familiarity with Federal AI Executive Orders, NIST AI Risk Management Framework (RMF), and secure enclaves (FedRAMP High / GovCloud).
- Active AWS Certified Solutions Architect or Machine Learning Specialty certifications.
Education Requirement - Bachelor's or Master's degree in Computer Science, Artificial Intelligence, Data Science, Software Engineering, or a related technical discipline.
Benefits
- Health Insurance
- 401k match
- Unlimited Vacation
- 11 Federal Holidays
- Remote work
- Training
- Mentoring/Coaching
