AI Engineer – Financial Services

RiskSpan

AI Engineer developing production-grade applications in financial services using AWS technologies. Responsible for building scalable AI systems and integrating enterprise data solutions.

Posted 7/2/2026full-timeWashington • District of Columbia, Washington • 🇺🇸 United StatesMid-LevelSeniorWebsite

Core Competencies

Role fit

Core Competencies

Use this summary to align your resume positioning with the role.

Demonstrates expertise in designing and deploying AI-powered applications, with a strong focus on end-to-end solutions, integration with cloud services, and optimization of AI systems for performance and reliability. Proficient in Python programming, SQL, and leveraging AWS services for building robust AI architectures.

Highest-signal resume keywords

AI Application DevelopmentAWS Services (Lambda, ECS, S3, Step Functions, SQS/SNS)Python ProgrammingSQL QueryingRAG Architecture and Retrieval Pipelines

ATS Keywords

Tailor your resume

Applicant Tracking System Keywords

Tip: use these terms in your resume and cover letter to boost ATS matches.

Hard Skills

AI Application DevelopmentPython ProgrammingSQL QueryingRAG ArchitectureEmbedding TechniquesModel Performance EvaluationData TransformationPrompt EngineeringTool/Function CallingStructured Output Validation

Soft Skills

Problem-Solving

Tools & Technologies

AWS BedrockVector DatabasesData Pipeline ToolsChatbot FrameworksKnowledge Assistants

Industry Keywords

AI Systems IntegrationCloud DeploymentHuman-in-the-Loop WorkflowsFinancial Use CasesMulti-Agent Systems

Tech Stack

Tools & technologies

Amazon RedshiftAWSCloudPythonSQL

About the role

Key responsibilities & impact

Design, build, and deploy AI-powered applications including chatbots, knowledge assistants, and workflow automation agents.
Implement end-to-end solutions covering data ingestion, transformation, prompt orchestration, model interaction, and cloud deployment.
Integrate AI systems with internal APIs, enterprise platforms, and data pipelines.
Design agent workflows with tool/function calling, branching logic, retries, and fallback handling.
Implement human-in-the-loop and approval-based workflows for regulated financial use cases.
Build multi-agent systems for validation, refinement, and complex task decomposition.
Design and implement RAG pipelines covering chunking, embeddings, retrieval, and grounding.
Work with structured and unstructured data using SQL, S3, and data pipeline tools.
Leverage AWS services (S3, Glue, Redshift, Lambda, ECS, Step Functions, SQS/SNS) for storage, transformation, and orchestration.
Monitor and improve AI systems for accuracy, latency, cost, and reliability.
Implement structured output validation, schema enforcement, and guardrails.
Evaluate model performance and iteratively improve grounding and output consistency.

Requirements

What you’ll need

Strong experience building AI applications using LLMs (e.g., AWS Bedrock or equivalent platforms).
Hands-on experience with RAG architectures and retrieval pipelines.
Experience with vector databases, embeddings, and semantic search.
Demonstrated track record deploying production AI systems end-to-end — not just prototypes.
Solid Python programming skills (required).
Experience with core AWS services: Lambda, ECS, S3, Step Functions, SQS/SNS.
Strong SQL skills for querying and integrating structured data.
Experience integrating AI systems with APIs, databases, and cloud services.
Understanding of prompt engineering, tool/function calling, and structured outputs.
Strong problem-solving skills for building reliable systems around probabilistic AI behavior.

Benefits

Comp & perks

Flexibility in work arrangement
Professional development