Senior Software Engineer, Agentic AI

Invicti Security is a company focused on innovative security solutions, and they are seeking a Senior Software Engineer to join their AI team. In this role, you will design and implement autonomous agent systems, collaborate with cross-functional teams, and take ownership of features from design through production to enhance security capabilities.

Responsibilities:

• Multi-Agent System Development: Design and implement autonomous agent systems in Python using frameworks like AWS Strands Agents, with emphasis on orchestration, reasoning, and decision-making
• MCP Integrations: Create Model Context Protocol integrations connecting Octo to security tools, developer environments, and AI coding assistants like Cursor and GitHub Copilot
• LLM Prompt Engineering: Develop and refine prompt chains for real security use cases, including triage, prioritization, and remediation
• RAG & Memory Systems: Build retrieval-augmented generation pipelines and memory architectures that give agents a persistent, contextual understanding of customer environments
• End-to-End Ownership: Own features from design through production — build, test, deploy, and measure outcomes
• Cross-Team Collaboration: Work closely with product, platform engineering, security research, and infrastructure teams to ensure we're building what customers need
• Experimentation & Productization: Evaluate new AI/ML capabilities and determine how to bring them to production

Requirements:

• 5+ years of production software development experience with a track record of shipping high quality solutions
• Hands-on experience building LLM-powered applications, RAG systems, or agentic AI
• Strong Python proficiency with solid software engineering fundamentals
• Understanding of distributed systems, API design, and cloud-native architectures
• Experience with prompt engineering, embeddings, and vector databases
• End-to-end software development skills, including frontend development, building pipelines, tests, monitoring, and scalability
• Ability to balance engineering rigor with pragmatic delivery, embracing agentic coding tools like Claude Code to accelerate delivery
• Clear communication skills — you surface problems early and propose solutions
• Experience with agent frameworks (AWS Strands, LangGraph, AutoGen, CrewAI) in production environments
• Familiarity with MCP (Model Context Protocol) and AI tool integration patterns
• Background in application security, penetration testing, or security tooling
• Experience with Go or C# for performance-critical components
• Ability to build single-page applications using Vue.js
• AWS experience with Bedrock and Kubernetes deployments
• Familiarity with using GitLab for source control and CICD
• Knowledge of evaluation methodologies for LLM systems (benchmarks, red-teaming, human feedback)
• Experience building third-party product integrations using REST APIs
• Contributions to open-source AI/ML projects