> Markdown version of [/jobs/ext/3997063-senior-ai-software-engineer-agentic-ai-security-harness-engineering](https://www.wearedevelopers.com/jobs/ext/3997063-senior-ai-software-engineer-agentic-ai-security-harness-engineering). Every page supports `.md` or `Accept: text/markdown`. Links point to the HTML versions so they work for humans too. Agent guide: [/agents.md](https://www.wearedevelopers.com/agents.md). --- # Senior AI Software Engineer - Agentic AI / Security Harness Engineering - **Company:** INVENTSOFT LLC - **Location:** Austin, TX, United States - **Experience:** Expert - **Contract:** Contract - **Skills:** JavaScript (Programming Language), Application Programming Interfaces (APIs), Artificial Intelligence, Automation of Tests, Code Generation, Software Quality, Computer Programming, Continuous Integration, Data as a Services, Cursor, Dynamic Program Analysis, Identity and Access Management, Issue Tracking Systems, Python (Programming Language), Machine Learning, Software Architecture, Systems Development Life Cycle, Cloud Services, Security Software, Software Deployment, Software Engineering, Systems Integration, TypeScript, Enterprise Software Applications, Chatbots, GitHub Copilot, Retrieval-Augmented Generation, Large Language Models, Claude Code, Multi-Agent Systems, Prompt Engineering, AI Coding Agents, Agentic-AI, Graphql, Invoking Functions, Api Design, Restful APIs, Model Context Protocol, Webhooks, Software Version Control, Human in the Loop, Static Application Security Testing, Vulnerability Analysis, Dynamic Application Security Testing - **Published:** October 28, 2026 - **Apply:** https://www.dice.com/job-detail/07d7bb4d-04b8-4a99-b028-063a524af878 ## About the Role Experience: 8+ years of software engineering experience required Critical Requirement: Minimum 12 months of hands-on production AI-agent engineering experience Required Skills and Qualifications * Minimum 12 months of hands-on experience building AI agents that are running in production for an employer or client. * Production agent experience must involve substantive agent engineering such as: + Agent loops. + Tool/function calling. + Multi-step orchestration. + Autonomous or semi-autonomous decision workflows. + Production deployment and operational ownership. * Candidate experience should demonstrate specific production evidence, preferably including: + Named or clearly described production system/use case. + Dates of hands-on agent development. + Users, transactions, workflows, requests, documents, or other relevant scale/volume. + Measurable technical, operational, or business results. * RAG chatbots/search solutions alone do not satisfy the production-agent requirement. * Classic machine learning, standalone RAG/search, proofs of concept, personal projects, research projects, or experimental prototypes do not count toward the required 12 months of production agent experience. * Using AI coding assistants such as GitHub Copilot, Claude Code, Cursor, or similar tools does not by itself constitute AI-agent engineering experience. * 8+ years of professional software-engineering experience with direct ownership of production systems. * Demonstrated experience developing and deploying AI-based solutions in production environments with measurable business or operational impact. * Strong programming proficiency in Python, TypeScript/JavaScript, Go, or comparable languages, with strong software-engineering practices covering testing, code quality, modularity, maintainability, and production support. * Hands-on experience with modern AI/LLM development, including: + Context engineering: designing what enters and informs the model context, including enterprise grounding, agentic retrieval/search, memory architectures, and structured outputs. + Agentic system design: agent-loop engineering, tool/function calling, multi-step orchestration, and multi-agent/sub-agent patterns. + Context-window management and token budgeting. + Cost and latency optimization for production AI workloads. + Evaluation of AI-system quality, reliability, safety, and policy compliance. * Solid understanding of software architecture and distributed-system design, including API design, service boundaries, event-driven patterns, data modeling, scalability, resiliency, and observability. * Experience developing and/or deploying applications with significant enterprise-scale impact, such as: + Broad internal or external user adoption. + High transaction/request volume. + Large enterprise deployment. + Organization-wide adoption. + Business-critical production workloads. * Experience integrating AI solutions across multiple enterprise systems and platforms using REST/GraphQL APIs, event-driven integrations, CI/CD systems, cloud services, identity platforms, security tooling, and internal enterprise services. * Demonstrated ability to independently own the full delivery lifecycle from requirements and architecture through implementation, deployment, production monitoring, and stakeholder engagement. * Strong communication and collaboration skills with the ability to explain architecture, implementation choices, risks, and trade-offs to engineering, security, product, and business stakeholders. * Working knowledge of secure-development practices and experience designing solutions that meet enterprise security and compliance requirements. ## Description * Design, build, and deploy production AI-powered capabilities across the software development lifecycle (SDLC), including: + Spec-Driven Development workflows that translate well-formed specifications into secure, verifiable implementations. + Assurance of AI-generated code through guardrails, policy enforcement, automated testing, security validation, and verification of code produced by AI assistants and agents. + SDLC skills and agent tooling that provide developer assistance as well as automated security verification, including design review, dependency and software supply-chain analysis, static/dynamic analysis orchestration, security gates, and release-audit support. * Design, build, and operate production AI-agent systems, including: + Agent loops involving reasoning, planning, tool execution, evaluation, and iterative decision-making. + Tool/function calling against enterprise applications and services. + Multi-step workflow orchestration. + Multi-agent and/or sub-agent orchestration where appropriate. + Human-in-the-loop and approval workflows for sensitive or high-risk operations. + Failure handling, observability, auditability, and operational controls required for reliable production deployment. * Build Security Harness capabilities around AI-assisted development and autonomoagentic workflows, including: + Policy enforcement and guardrails. + Controlled tool access and authorization. + AI-generated code assurance. + Automated security verification. + SAST, DAST, dependency, and software supply-chain analysis. + Security and release gates. + Threat modeling and secure design reviews. + Audit evidence, observability, and release validation. * Integrate AI agents and services with enterprise systems including source control, CI/CD platforms, ticketing systems, security scanning tools, identity platforms, data services, and internal applications through APIs, webhooks, event-driven integrations, and protocols such as MCP (Model Context Protocol). * Design context-engineering strategies for production AI systems, including enterprise grounding, agentic retrieval/search, memory architectures, structured outputs, context-window management, and token budgeting. * Optimize AI systems for production considerations including latency, cost, reliability, scalability, availability, security, and maintainability. * Define and implement evaluation approaches for AI-agent quality, reliability, safety, tool-use correctness, and policy compliance. * Partner with engineering, security, product, architecture, and leadership stakeholders to define requirements, evaluate technical trade-offs, and support enterprise adoption. * Apply sound architecture and systems-design practices including well-defined service boundaries, scalable APIs, appropriate data models, event-driven patterns, secure defaults, observability, resiliency, and extensibility. * Own solutions across the complete delivery lifecycle, including requirements analysis, architecture, implementation, testing, deployment, production support, monitoring, and continuous improvement.