Agentic AI Engineer

Key Responsibilities

• Handle large volumes of security event data
• Operate with resilience in noisy, real-world environments
• Continuously evolve as new attack patterns and tools emerge
• Improve and harden existing agentic systems
• Work with LLMs in production environments, not just prototypes
• Engineer robust context pipelines for large-scale data ingestion and reasoning
• Optimize systems for performance, reliability, and failure handling
• Evaluate and integrate new agent frameworks, tools, and approaches
• Rapidly hypothesize -> build -> test -> validate -> iterate

Skills, Knowledge, and Expertise

• Strong Python (or equivalent modern language) engineering skills.
• Deep understanding of language performance and internals (eg. GIL, concurrency tradeoffs, memory constraints).
• Proven experience building production-grade AI agents. Not just demos. Systems that run, recover, and scale.
• Thorough understanding of LLMs and agentic systems. You understand how they actually work under the hood.
• Strong context engineering skills. Able to curate, compress, and structure large datasets for
  effective LLM use.
• Experience evaluating, testing, and monitoring agents and LLM interactions using the latest
  techniques or frameworks.
• Experience handling large-scale high-volume data workflows.
• Portfolio of shipped work (GitHub, case studies, or equivalent).
• Bachelor of Computer Science/Engineering or above.
• Must be a US Citizen.

• Experience with cybersecurity tools (CrowdStrike, Splunk, Mandiant, etc.)
• Familiarity with multiple agent frameworks (Claude Agent SDK, LangGraph, AutoGen, custom systems, etc.)
• Experience evaluating tradeoffs between frameworks vs. custom orchestration.

Why DeepSeas?

• We are client obsessed. 
• We stand in solidarity with our teammates.
• We prioritize personal health and well-being.
• We believe in the power of diversity.
• We solve hard problems at the speed of cyber.

• Understanding and following DeepSeas’s information security policies and procedures.
• Remaining vigilant and reporting any suspicious activity or possible weaknesses in DeepSeas’s information security.
• Actively participating in DeepSeas’s efforts to maintain and improve information security.
• DeepSeas considers this position is as Moderate Risk with a potential to view/access/download restricted/private client/internal data. 
• This information must be treated with sensitivity and in the most secure manner. 
• HR reserves the right to perform random background/drug screens to ensure the safety of client/DeepSeas data

About
With nearly 30 years of experience in cyber defense, DeepSeas is trusted by 350+ clients, including Fortune 100 enterprises and mid-market organizations. Leveraging deep expertise that combines world-class cyber threat detection and response with industry-leading analysts, tailored threat intelligence, and accredited incident responders, DeepSeas is always on, always watching. Its Managed Detection & Response offering, DeepSeas MDR+, is anchored by its acquisition of Booz Allen Hamilton’s commercial Managed Threat Services (MTS) business in 2022. DeepSeas is the first and only MDR provider that covers the entire converged attack surface for the mid-market, including OT, IT, cloud, and mobile. Its full-spectrum cyber threat monitoring service is award-winning and backed by world-renowned researchers, data scientists, and mathematicians who have published over 250 papers and created a broad base of intellectual property, while achieving a number of scientific breakthroughs in the areas of big data, machine learning, and artificial intelligence as it applies to the detection of advanced and unknown cyber threats.