Senior AI Application Engineer

EVERSANA • New York, NY

4d

About The Position

EVERSANA is hiring an AI / Agent Application Engineer to build its agentic workforce. Working under the guidance of the Chief AI & Analytics Officer, the engineer will develop AI agents, create APIs and tools for agents to use, and optimize data pipelines that provide context to AI. The role involves designing and implementing scalable multi-agent systems to automate complex business processes, translating existing processes into agentic solutions, and developing new multi-agent architectures. The engineer will also implement secure tool-calling and apply LLMOps/AgentOps practices while mitigating AI-specific security risks. The position requires 40 hours per week, Monday through Friday, and some travel may be required to meet with clients, stakeholders, or off-site personnel and management.

Requirements

• Ph.D. in Computer Science, Engineering, Mathematics, Physics, Artificial Intelligence, Software Engineering, or a closely related field.
• 1–7+ years of software engineering experience.
• Expert-level proficiency in Python and/or TypeScript.
• Experience with MCP architectures.
• Proficiency in Rust.
• Deep understanding of agentic design patterns, such as ReAct, Plan-and-Solve, Reflection, and Tree of Thoughts.
• Extensive experience with LLM APIs such as OpenAI, Anthropic, and Google Gemini, and open-weights models such as Llama 3 and Mistral.
• Experience with vector and graph databases.
• Experience with RAG architectures, such as GraphRAG and hybrid search.
• Strong background in cloud architecture (AWS, GCP, or Azure) and containerization (Docker/Kubernetes).

Nice To Haves

• Experience with enterprise-scale deployment of multi-agent architectures.
• Expert-level proficiency in Rust.
• 3+ years specifically in generative AI, LLMs, or cognitive architectures.
• Extensive experience with RAG architectures, such as GraphRAG and hybrid search.

Responsibilities

• Architect, design, and implement scalable multi-agent systems that automate complex, multi-step business processes.
• Translate existing processes into agentic solutions and develop novel multi-agent architectures for new opportunities.
• Implement agentic solutions using orchestration frameworks such as Google ADK, LangGraph, and CrewAI.
• Design secure tool-calling architectures that allow LLMs to safely interact with internal databases, CRMs, and APIs.
• Implement LLMOps and AgentOps best practices.
• Mitigate AI-specific security risks, including prompt injection, hallucination loops, and unauthorized tool execution.
• Demonstrate commitment to diversity, equity, and inclusion through ongoing development, inclusive behavior, and proactive bias management.
• Perform other duties as assigned.

What This Job Offers

• Job Type: Full-time
• Career Level: Mid Level
• Education Level: Ph.D. or professional degree