Generative AI Engineer

Thunderhawk Technology Partners; Pennington (NJ); On-site; USD 100,000 - 130,000; Full time

Job summary

Thunderhawk Technology Partners is looking for an AI Agent Development Engineer for a financial services client in Pennington, NJ. This long-term contract role involves designing and deploying intelligent AI agents and automating business workflows. Candidates must have 3-8+ years of AI/ML engineering experience, a degree in a relevant field, and skills in LLMs, prompt engineering, and cloud platforms like Azure AI. This position is onsite only, intended for US Citizens or Permanent Residents.

Qualifications

• 3–8+ years of experience in AI/ML engineering or software development.
• Hands-on experience building AI agents, chatbots, or intelligent automation systems.
• Proven ability to deploy solutions into production environments.

Responsibilities

• Design and implement AI agents leveraging LLMs and RAG frameworks.
• Develop conversational AI solutions and intelligent automation workflows.
• Integrate AI agents with enterprise systems and monitor performance.

Skills

Experience with LLMs

Prompt engineering

Cloud platforms (Azure AI)

Understanding of microservices

Experience with vector databases

Education

Bachelor’s or Master’s degree in Computer Science, AI, Data Science, or related field

Tools

LangChain

Azure AI

Docker

Kubernetes

Job description

This is a long-term contract opportunity.

No visa candidates. Only US Citizens or Permanent Residents will be considered for this role.

Local candidates only. This is an onsite role.

We are seeking a highly skilled AI Agent Development Engineer for a financial services client to help them design, build, and deploy intelligent AI agents that automate business workflows and enhance decision‑making. This role focuses on developing agent‑based solutions using large language models (LLMs), copilots, and enterprise AI platforms to drive operational efficiency and innovation.

Key Responsibilities

• Design and implement AI agents leveraging LLMs, Retrieval‑Augmented Generation (RAG), and multi‑agent frameworks
• Develop conversational AI solutions, copilots, and intelligent automation workflows
• Integrate AI agents with enterprise systems (APIs, Dynamics 365, Dataverse, Microsoft Fabric and MCP’s)
• Build agent orchestration including memory, context management, and reasoning capabilities
• Monitor, evaluate, and continuously improve agent performance and reliability
• Apply Responsible AI, security, and governance standards across all solutions
• Collaborate with business and technology teams to translate requirements into agent‑driven solutions

Required Skills

• Experience with LLMs, prompt engineering, embeddings, and RAG architectures
• Familiarity with frameworks: LangChain, Semantic Kernel, AutoGen, or similar
• Cloud platforms: Azure AI (preferred), AWS, or GCP
• Experience with vector databases (Pinecone, FAISS, Azure AI Search, etc.)
• Understanding of microservices, containers (Docker, Kubernetes)

Qualifications

• Bachelor’s or Master’s degree in Computer Science, AI, Data Science, or related field
• 3–8+ years of experience in AI/ML engineering or software development
• Hands‑on experience building AI agents, chatbots, or intelligent automation systems
• Proven ability to deploy solutions into production environments

Preferred Qualifications

• Experience with Copilot Studio, Agent 365, or enterprise AI platforms
• Knowledge of knowledge graphs and enterprise data platforms (e.g., Microsoft Fabric)
• Domain experience in Financial Services / Wealth Management
• Familiarity with AI governance, compliance, and audit frameworks