Architect, design, and implement AI-powered agents capable of reasoning, learning, and acting autonomously to achieve defined objectives.
Develop agent behaviors using techniques such as reinforcement learning, natural language processing (NLP), knowledge representation, planning, and decision-making algorithms.
Integrate AI agents with existing software systems, data sources, and user interfaces to enable seamless operations across platforms.
Conduct rigorous testing and evaluation of AI agent performance, robustness, and security in simulated and real-world scenarios.
Collaborate with data scientists, software engineers, and subject matter experts to curate and preprocess training data, and fine-tune agent models for optimal performance.
Analyze user and system requirements to customize AI agent workflows for specific government or enterprise use cases.
Develop tools for monitoring, visualization, and management of AI agent interactions and results.
Ensure compliance with government security, privacy, and ethical guidelines throughout the AI agent lifecycle.
Prepare detailed technical documentation, including design specifications, integration guides, and user manuals.
Stay current with advances in AI agent frameworks, machine learning algorithms, and relevant research to continuously enhance agent capabilities.
Provide technical expertise and guidance during project planning, system integration, and post-deployment support.

Requirements

4 years of experience in AI/ML engineering or advanced data science.
4 years of proven track record building and deploying production-grade autonomous agents.
4 years of strong experience in context engineering.
4 years of deep experience with LangChain, LangGraph, CrewAI, or AutoGPT.
4 years of experience implementing Retrieval-Augmented Generation (RAG) architectures using vector databases.
4 years of proficiency in Python and AI/ML libraries (OpenAI, Hugging Face, Azure AI).
4 years of experience integrating Large Language Models (LLMs) via APIs, with knowledge of AI governance, model lifecycle management, and evaluation.
4 years of experience implementing and extending the Model Context Protocol (MCP) to provide LLMs with secure, standardized access to local and remote data sources, as well as experience implementing AI guardrails, content filtering, and safety controls.
4 years of understanding data privacy and handling of sensitive data, including PII and PHI.
Must be able to pass a background check.
May require additional background checks as required by projects and/or clients at any time during employment.

Benefits

Medical, Dental and Vision Insurance
Wellness Program
Flexible Spending Accounts (Healthcare, Dependent Care, Commuter)
Short-Term and Long-Term Disability options
Basic Life and AD&D Insurance (Company Provided)
Voluntary Life and AD&D options
401(k) Retirement Savings Plan with matching after one year
Paid Time Off

Applicant Tracking System Keywords

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

Hard Skills & Tools

AI engineeringmachine learningreinforcement learningnatural language processingknowledge representationdecision-making algorithmscontext engineeringRetrieval-Augmented GenerationPythonAI/ML libraries

Soft Skills

collaborationtechnical expertisecommunicationproblem-solvingdocumentation