Skip to main content

Agentic Automation Engineer

Posted today

infocap aiHonolulu (HI)

SENIORITY

Lead

Apply (opens in a new tab)

About the role

U.S.-BASED CANDIDATES ONLY. All work must be performed within the United States. U.S. work authorization and the ability to successfully complete the required government background investigation are mandatory. Our mission is to co-innovate solutions which solve critical challenges and drive extraordinary value. Infocap is a trusted partner to government agencies and commercial enterprises within regulated industries. We are passionate about collaboration and technology-enabled innovation to empower our customers to achieve meaningful results. Infocap develops human-centric automation for government and regulated organizations. We combine document intelligence, agentic AI, process orchestration, and decision intelligence to improve how complex work gets done. We deliver solutions which unlock the potential of the human workforce, while ensuring every automated outcome is ethical, explainable, appealable, and accountable. Infocap is a small business delivering big results, supporting agencies through enhancing efficiency, reducing costs, and improving the consumer experience. We are a team of doers, who plan, architect, test, build, and support what we create. But at our core we're problem solvers, approaching every challenge with innovative thinking and creativity. We invest in coaching, training, and the cultivation of thought leadership across our team. We foster an environment of exploration and experimentation with emerging technologies and advanced methods.
THE OPPORTUNITY: We are seeking an Agentic Engineer who can turn business requirements into secure, reliable AI solutions. You will own hands-on engineering from architecture and prototyping through deployment, evaluation, operational support, and improvement. Amazon Bedrock AgentCore is the core technical requirement, supported by practical implementation experience with AWS Quick and Amazon Connect. You will work with customers and delivery teams to make AI useful in consequential workflows while preserving human accountability, transparent decisions, and agency control.
WHAT YOU WILL DO: ·
Design, build, and operate agents using Amazon Bedrock AgentCore, selecting appropriate Runtime, Gateway, Identity, Memory, and Observability capabilities.· Develop agents that retrieve information, use tools, produce structured outputs, and coordinate multistep workflows through reliable APIs and enterprise integrations.· Configure and integrate AWS Quick capabilities for research, business insights, knowledge access, and workflow automation, with appropriate permissions and output validation.· Implement Amazon Connect conversational and agent-assistance workflows, integrating knowledge sources and backend systems while preserving context during human handoffs.· Connect AI solutions to document-processing, case-management, and business systems using relevant AWS services, such as Lambda, S3, and Step Functions.· Combine AI reasoning with deterministic business rules, explicit approval gates, human review, escalation, and recovery paths for consequential actions.· Apply least-privilege access, secure credential handling, sensitive-data protection, prompt-injection defenses, controlled tool execution, and audit logging.· Build evaluation datasets and track groundedness, task completion, tool correctness, failure rates, latency, cost, and operational outcomes.· Use infrastructure as code, CI/CD, monitoring, and documented procedures to support reliable releases and ongoing operations.· Validate service availability and deployment suitability for each customer environment; explain technical choices, limitations, and tradeoffs clearly.
REQUIRED QUALIFICATIONS:
  • Demonstrable Amazon Bedrock AgentCore experience, including at least one working implementation deployed to production or a substantial operational pilot. Experience limited to general Bedrock model usage, Amazon Bedrock Agents, prompt engineering, coursework, or certifications does not fulfill this requirement.· Ability to explain your AgentCore architecture and personal contribution: deployment through Runtime; tool and API integration through Gateway and/or Model Context Protocol (MCP) where applicable; identity and authorization; credentials; session state and memory; and tracing, evaluation, and debugging.· Evidence of a meaningful engineering tradeoff or failure you resolved, plus observed results such as improved task success, reduced manual effort, reliability, latency, or cost.· Practical AWS Quick implementation or integration experience involving enterprise information, research, insights, or automation. Be ready to distinguish what you configured or integrated from ordinary end-user usage.· Practical Amazon Connect implementation experience with agentic customer-service or employee-assistance workflows, including integrations, human escalation, and operational monitoring.· Strong Python engineering, API integration, version control, testing, and debugging; proficiency with at least one suitable agent framework, such as Strands Agents or LangGraph.· Working knowledge of retrieval-augmented generation, tool calling, context management, AWS security controls, infrastructure as code, and CI/CD.· Ability to collaborate with business stakeholders and communicate technical decisions clearly.· Current U.S. residence, authorization to work in the U.S., and ability to meet the location and government background-investigation requirements below.
PREFERRED QUALIFICATIONS:
  • Delivery experience in government or other regulated environments.· AWS GovCloud familiarity and practical awareness of NIST and FedRAMP controls.· Intelligent Document Processing (IDP) and document intelligence, case management integration, workflow automation expertise and experience.· Advanced use of AgentCore Evaluations, Policy, Browser, or Code Interpreter.· Experience measuring automation outcomes and improving deployed agents through structured evaluation. LOCATION AND ELIGIBILITYCandidates must currently reside in the United States and perform all work from within the United States. Candidates must be legally authorized to work in the United States and be willing and able to undergo and successfully complete the government background investigation required for assigned work, maintaining any resulting suitability or access eligibility.

Before you apply

Applying takes about a minute. These four things decide how fast it moves after that.

Your profile is current

It's what we read first. Occupations, seniority and locations matter more than a long history.

Two examples you can talk through

Not a portfolio — just two pieces of work where you can explain the decisions and what you'd change.

A number in mind

What you're on now and what would make you move. We negotiate better when we know both.

Your notice period

Employers plan around it, and it's the question that stalls offers most often.

Once you apply, someone reads it and calls you before anything reaches the employer — usually within two working days.

More like this