Data & ML Engineer

About Our Client

The organization operates in the field of insights and resilient optimization of complex systems. It leverages artificial intelligence, mathematical optimization, data analytics, and software engineering to help customers align outcomes with operational goals and make better decisions. The organization addresses challenges related to anticipating, assessing, and mitigating the impacts of disruptions in dynamically changing environments.

About the Opportunity

The Data & ML Engineer role focuses on building the data and model layers behind an AI-enabled decision-support system within an accredited environment. This position is responsible for managing data ingestion, record resolution against a shared data model, relevance scoring, and generating actionable, explainable outputs. The role contributes by enhancing decision-making capabilities through robust data processes, traceability, and probabilistic record matching, supporting accountable and reliable system outputs.

Responsibilities

• Design and maintain the graph of entities, records, and typed relationships
• Implement probabilistic record matching including blocking, candidate generation, pairwise scoring, clustering, and threshold policy
• Build deduplication and known-record suppression mechanisms
• Establish provenance tracking for all data nodes and edges
• Produce detailed interface and data-flow documentation
• Develop relevance and priority models for large, imperfect record sets
• Own calibration, threshold design, and abstention policies
• Conduct feature engineering, baseline establishment, and error analysis accounting for false positive and negative costs
• Implement embeddings, vector storage, and retrieval across provenance-tracked evidence
• Integrate language models via managed services and maintain alternatives
• Design prompts and output schemas
• Bind generated text to cited sources and handle "insufficient evidence" responses appropriately
• Manage model packaging, serving, versioning, and rollback
• Build secure pipelines for data ingestion, transformation, validation, and publishing
• Implement quality checks, schema validation, lineage capture, and audit logging
• Establish source drift detection
• Generate synthetic data to support development
• Adhere to engineering standards set by the Data Lead, including documentation and telemetry
• Maintain audit trails covering recommendations, overrides, and model versions
• Submit changes through gated release processes

Requirements

• Minimum 5 years experience in data engineering, machine learning engineering, or production analytics
• Proficient in Python and SQL with experience handling large, imperfect operational data
• Experience delivering systems for sustained operational use
• Regular use of AI-assisted development tools with sound judgment
• Ability to explain technical decisions to non-technical stakeholders
• US Citizenship and active US Secret clearance with CAC eligibility
• Willingness to travel up to 25% to various sites
• Active Top Secret clearance
• Experience with probabilistic matching of inconsistent identity data