Senior AI Engineer

Summary:

We are looking for a Senior AI Engineer with deep experience in building LLM-powered agents to join our AI Engineering team. You will design and ship agentic systems that reason over data security signals, automate investigation and recovery workflows, and surface insights to our customers and internal teams. This is a hands-on engineering role for someone who has taken GenAI agents from prototype to production and can own systems end to end.

Responsibilities:

• Build agents: Design, build, and deploy production-grade LLM/GenAI agents — including multi-step reasoning, tool use, orchestration, and memory — that operate reliably at enterprise scale.
• Engineer in Python: Develop and maintain agent frameworks and pipelines in Python, integrating LLMs with internal tools, APIs, and data sources.
• Configure with YAML: Author and manage YAML-based configurations for agent behaviors, prompts, workflows, and deployment pipelines.
• Ensure quality: Establish evaluation, guardrails, observability, and testing practices to ensure agent accuracy, safety, and cost-efficiency.
• Collaborate: Partner with product, security research, and platform teams to translate requirements into robust agentic solutions.
• Lead: Mentor engineers, drive technical design reviews, and set best practices for agent development across the organization.

Requirements:

• Experience: 7&ndash10 years of software/AI engineering experience, with a strong track record of shipping systems to production.

Required Skills:

• Python: Expert-level Python — clean, well-tested, production-quality code and strong grasp of software design.
• Agent building: Hands-on experience building LLM/GenAI agents, including agent frameworks (e.g., LangChain, LangGraph, CrewAI, or similar), tool/function calling, RAG, and prompt engineering.
• YAML: Proficiency with YAML for configuration, workflow definition, and infrastructure/deployment tooling.
• LLMs: Experience with LLM APIs and models (e.g., Anthropic Claude, OpenAI, open-source models) and understanding of their trade-offs.
• Rigor: Solid understanding of evaluation, observability, and safety/guardrails for agentic systems.
• Cloud & infra: Familiarity with cloud platforms (AWS/Azure/GCP), containers, and CI/CD.

Preferred Skills:

• Domain: Experience in data security, cybersecurity, or data management domains.
• OSS: Contributions to open-source agent or ML tooling.
• Retrieval: Experience with vector databases, embeddings, and retrieval systems.
• Scale: Background in MLOps or distributed systems.

#AditiConsulting
# 26-04827