Gen AI Developer
Job Description
Our client, an international AI development company based in New York, is currently seeking a Gen AI Developer to lead strategic product development efforts in a fast-paced and collaborative environment.
This role requires hands-on development experience with tools such as Langchain, LangGraph, CrewAI, and Google Gemini Agent Builder. The ideal candidate will have a strong programming background, a deep understanding of coordination and reasoning strategies in AI systems, and familiarity with cloud platforms and modern CI/CD practices.
Key Responsibilities
Multi-Agent AI Development:
Design and implement multi-agent AI systems using frameworks like CrewAI, LangGraph, and Langchain
Develop agent-based workflows and orchestration logic leveraging agentic design patterns
Prompt Engineering & Reasoning Strategies:
Apply ReAct prompting and Chain-of-Thought reasoning to enhance AI output quality
Assist in fine-tuning LLMs and optimizing prompt-response workflows for task accuracy
Model Integration & Cloud Deployment:
Build and deploy models using Google Cloud and Vertex AI
Implement CI/CD pipelines to support automated model deployment and evaluation
Performance Evaluation & Optimization:
Evaluate AI model performance for accuracy, efficiency, and scalability
Write and maintain evaluation code to benchmark model behavior in distributed environments
Optimize agent coordination and response logic for real-time use cases
Research & Collaboration:
Stay current with advancements in generative AI, multi-agent coordination, and distributed reasoning
Collaborate with cross-functional teams to integrate AI services into product workflows
Qualifications & Skills
1+ years of experience in AI application development
Proficiency in Python or Java for AI system development
Hands-on expertise with Langchain, LangGraph, CrewAI, and Gemini Agent Builder
Experience with ReAct prompting, Chain-of-Thought reasoning, and model fine-tuning
Familiarity with Vertex AI, Google Cloud services, and CI/CD automation tools
Understanding of reinforcement learning, distributed AI, and multi-agent system design
Strong analytical and troubleshooting skills for debugging complex AI workflows
Collaborative team player with effective communication skills
Self-motivated, fast learner, and comfortable working in a dynamic R&D environment
Very strong English communication skills, both written and verbal (essential for global collaboration)
What you'll do
- Design, train, and evaluate large language models and agentic pipelines
- Build production-grade inference and orchestration systems
- Collaborate with product and engineering teams to ship AI features end-to-end
- Run experiments, benchmark models, and iterate on prompt and fine-tuning strategies
- Own model quality, latency, and cost across the stack
- Mentor engineers and contribute to internal ML platform improvements
What we're looking for
- Strong background in machine learning, NLP, or deep learning
- Hands-on experience with PyTorch, Hugging Face, or similar frameworks
- Experience deploying models to production
- Solid Python engineering skills
- Familiarity with RAG, vector databases, and agent frameworks
- Strong communication skills in English
Nice to have
- Published research or open-source contributions
- Experience with distributed training or GPU optimization