AI Product Engineer

AI Product Engineer at CognitivTrust (via Uplers)

CognitivTrust is seeking an AI Engineer to design and build fully autonomous agents for their security platform. This role focuses on creating production-grade agentic systems that analyze code, identify vulnerabilities, and orchestrate remediation without human intervention. You will be instrumental in building the security infrastructure layer for the Agentic SDLC era, ensuring safety and speed in AI-driven software development.

What You'll Do:

• Design and implement autonomous agents for security analysis, threat modeling, and remediation.
• Build multi-agent orchestration systems with configurable autonomy levels.
• Develop agent runtime infrastructure including memory, planning, and tool use.
• Create evaluation frameworks to measure agent reliability and safety.
• Integrate agents with MCP (Model Context Protocol) for seamless tool connectivity.
• Ship production systems that run unsupervised in enterprise environments.

What You Bring:

Core Engineering:

• Strong software engineering fundamentals, particularly in Python and distributed systems.
• Experience building and deploying production systems at scale.
• Deep understanding of agent architectures (ReAct, tool use, planning, reflection).

Enterprise Agent Experience:

• Proven experience building and deploying autonomous agents in enterprise production environments.
• Implemented end-to-end agentic workflows with minimal human oversight.
• Designed agents that integrate with enterprise systems (APIs, databases, SaaS platforms) handling authentication, rate limits, and failure recovery.
• Experience with agent observability (logging, tracing, debugging autonomous systems).
• Built human-in-the-loop checkpoints and escalation paths for critical agent decisions.

Agentic Systems Design:

• Hands-on experience designing multi-agent systems with clear task decomposition and coordination.
• Implemented configurable autonomy levels.
• Built evaluation and testing frameworks for non-deterministic agent behavior.
• Experience with agent memory systems (short-term context, long-term knowledge, retrieval).
• Familiarity with agent frameworks (LangGraph, CrewAI, AutoGen) or custom orchestration layers.

Bonus Points:

• Security domain knowledge (AppSec, DevSecOps, vulnerability management).
• Experience with MCP or similar agent-tool protocols.
• Background in enterprise software or B2B SaaS.

What Sets You Apart:

• You've built agents that run autonomously in production for weeks.
• You think in systems: reliability, observability, failure modes, edge cases.
• You are obsessed with evaluation and understand the limitations of 'vibes-based' testing.
• You understand enterprise requirements like auditability, compliance, and minimizing surprises.
• You ship fast and iterate based on real-world feedback.

Key Skills/Competency:

• Agentic AI
• Agentic AI Workflows
• CyberSecurity
• DevSecOps
• AppSec
• Python
• Distributed Systems
• Agent Architectures
• CrewAI
• LangChain