AI Security Developer
Summary
Develops and secures AI systems by integrating vendor solutions, deploying LLM frameworks on cloud, and building Python-based tools to protect AI agents and enterprise infrastructure.
Responsibilities:
Experience - upto 5 years
- Integrate vendor AI security solutions with the firm’s enterprise infrastructure, platforms, APIs, identity systems, and deployment pipelines.
- Deploy, configure, and support LLM inference frameworks on Microsoft Azure or other cloud environment, ensuring scalability, reliability, security, and operational readiness.
- Develop Python-based services, APIs, automation scripts, integration components, and tooling to support AI security and LLM platform capabilities.
- Build solutions that enhance the firm’s security posture across LLM applications, AI agents, developer workflows, and enterprise AI infrastructure.
- Collaborate with security, infrastructure, platform engineering, cloud, and application development teams to deliver secure and production-ready AI capabilities.
- Work closely with teammates to design technical solutions, review implementation approaches, troubleshoot issues, and support delivery milestones.
Technical Skills Required
- Strong programming skills in Python.
- Hands-on experience developing AI agents or LLM-powered applications.
- Familiarity with agent development frameworks such as:
- OpenAI Agents SDK
- Google Agent Development Kit
- LangGraph
- Similar agent orchestration frameworks
- Familiarity with AI coding assistants such as Claude Code, GitHub Copilot, or equivalent tools.
- Understanding of core LLM concepts, AI agent concepts, and agentic workflow patterns.
- Basic understanding of Agentic AI security, LLM security, and common AI security risks.
- Familiarity with OWASP AI / LLM threats, including prompt injection, sensitive information disclosure, insecure plugin or tool use, excessive agency, and model misuse.
- Familiarity with the concepts of AI gateways and MCP gateways.
- Experience with OpenTelemetry or similar logging, tracing, and observability tools.
- Good knowledge of Linux, shell scripting, Git, Docker, and Kubernetes.
- Experience working with APIs, microservices, CI/CD pipelines, and cloud or containerized environments.
- Ability to work with security, infrastructure, and application teams to deliver secure enterprise AI capabilities.