we are looking for a Senior AI Engineer.
Responsibilities:
– Design and develop LLM-powered security features and internal AI tools, including RAG pipelines, multi-agent workflows, and prompt-engineered systems for cybersecurity use cases
– Architect and operate multi-agent systems in production – covering orchestration, inter-agent communication, task delegation, and failure handling at scale
– Build agent monitoring and observability pipelines, including tracing, drift and failure detection, alerting, and reliability SLA management
– Build and maintain scalable MLOps infrastructure – model serving, evaluation frameworks, experiment tracking, and CI/CD for ML
– Fine-tune and adapt foundation models on internal datasets such as network telemetry, security logs, and threat intelligence
– Establish and champion best practices for model observability, safety, and responsible AI deployment
– Stay current with the LLM/GenAI ecosystem and drive continuous improvements to the AI SDLC and AI Research cycle
Responsibilities:
– Design and develop LLM-powered security features and internal AI tools, including RAG pipelines, multi-agent workflows, and prompt-engineered systems for cybersecurity use cases
– Architect and operate multi-agent systems in production – covering orchestration, inter-agent communication, task delegation, and failure handling at scale
– Build agent monitoring and observability pipelines, including tracing, drift and failure detection, alerting, and reliability SLA management
– Build and maintain scalable MLOps infrastructure – model serving, evaluation frameworks, experiment tracking, and CI/CD for ML
– Fine-tune and adapt foundation models on internal datasets such as network telemetry, security logs, and threat intelligence
– Establish and champion best practices for model observability, safety, and responsible AI deployment
– Stay current with the LLM/GenAI ecosystem and drive continuous improvements to the AI SDLC and AI Research cycle
Requirements:
– 5-8 years of software engineering experience, with 2-3 years focused on AI/ML
– Proven experience building and deploying production LLM applications (RAG, agents, tool-use, fine-tuning)
– Hands-on experience designing and operating production multi-agent systems
– Experience building agent observability and monitoring solutions
– Proficiency with LLM orchestration frameworks: LangChain, LangGraph, and/or AWS Bedrock AgentCore
– Strong Python programming skills
– Experience building and maintaining MLOps pipelines (model serving, eval frameworks, experiment tracking)
– Solid understanding of transformers, embeddings, and vector databases
– Experience with cloud infrastructure and Kubernetes
Soft Skills:
– Self-driven and proactive – able to establish best practices and drive initiatives independently
– Continuous learner who stays current with a rapidly evolving field and translates new knowledge into practical improvements
– Strong collaborator who works effectively across R&D and product team
Nice to Have / Advantage:
– Cybersecurity background (significant advantage)
– Networking domain knowledge (SDN, BGP)
– Experience with model evaluation methodologies (LLM-as-judge, RAGAS)
– Familiarity with Model Context Protocol (MCP)
– Background in telecom or enterprise SaaS environments
– Publications or open-source contributions in GenAI
– 5-8 years of software engineering experience, with 2-3 years focused on AI/ML
– Proven experience building and deploying production LLM applications (RAG, agents, tool-use, fine-tuning)
– Hands-on experience designing and operating production multi-agent systems
– Experience building agent observability and monitoring solutions
– Proficiency with LLM orchestration frameworks: LangChain, LangGraph, and/or AWS Bedrock AgentCore
– Strong Python programming skills
– Experience building and maintaining MLOps pipelines (model serving, eval frameworks, experiment tracking)
– Solid understanding of transformers, embeddings, and vector databases
– Experience with cloud infrastructure and Kubernetes
Soft Skills:
– Self-driven and proactive – able to establish best practices and drive initiatives independently
– Continuous learner who stays current with a rapidly evolving field and translates new knowledge into practical improvements
– Strong collaborator who works effectively across R&D and product team
Nice to Have / Advantage:
– Cybersecurity background (significant advantage)
– Networking domain knowledge (SDN, BGP)
– Experience with model evaluation methodologies (LLM-as-judge, RAGAS)
– Familiarity with Model Context Protocol (MCP)
– Background in telecom or enterprise SaaS environments
– Publications or open-source contributions in GenAI
This position is open to all candidates.
