Explicitly requires vibe coding: building agentic LLMs, tool-calling/function-calling agents, RAG and multi-agent orchestration.
About the Role
Azurity Pharmaceuticals is hiring an Agentic AI Developer to design, build, and deploy agentic LLM-based systems and multi-step autonomous workflows that integrate with internal and third-party systems, ensuring orchestration, observability, and regulatory safety controls. The role focuses on implementing tool-calling agents, retrieval-augmented pipelines, and multi-agent coordination to automate business workflows in a regulated environment.
Job Description
Role
Azurity is seeking an Agentic AI Developer to design, build, and deploy AI agents and multi-step autonomous workflows that integrate with internal systems and business processes. The role centers on creating agentic LLM workflows that perform planning, reasoning, tool calls, data retrieval, document generation, and cross-system orchestration while maintaining safety and compliance controls.
Key Responsibilities
- Design and build AI agents that use large language models to plan, reason, and execute multi-step tasks (data retrieval, document generation, cross-system workflows).
- Integrate agents with internal and third-party systems via APIs, MCP servers, and other tool-calling frameworks.
- Build and maintain orchestration layers for multi-agent workflows, including error handling, retries, and human-in-the-lead checkpoints.
- Implement evaluation, observability, and safety guardrails for AI systems in production.
- Translate business problems into technical solutions and communicate AI system behavior to non-technical stakeholders.
Requirements
- Three or more years of professional software development experience, including at least one year working directly with large language models or agentic AI systems.
- Strong proficiency in Python or a similar language and experience using LLM APIs such as Anthropic or OpenAI.
- Hands-on experience building tool-calling or function-calling agents, designing tool schemas, and managing multi-turn reasoning.
- Familiarity with agent orchestration concepts (e.g., ReAct, planning/reflection loops, multi-agent coordination).
- Experience with retrieval-augmented generation (RAG), vector databases, and embedding models.
- Solid understanding of API design, integration patterns, and asynchronous systems.
- Experience implementing evaluation, observability, and safety/compliance guardrails for production AI systems.
- Comfort working in regulated industries with attention to data privacy, security, and compliance.
- Strong communication skills for cross-functional collaboration.
Preferred Qualifications
- Experience in pharmaceutical, healthcare, or other regulated industries.
- Familiarity with Model Context Protocol (MCP) or similar tool-integration standards.
- Experience with enterprise systems common in pharma (Veeva, Salesforce, ERP, IT service management platforms).
- Background in prompt engineering and fine-tuning/evaluation of LLMs.
- Exposure to cloud platforms (AWS, Azure, or GCP) and MLOps practices.