AI Engineering Lead

AI Engineering Lead

Location - NYC, NY (Hybrid )

Only Banking,Financial OR Insurance Domain.

Employment Type - Fulltime

About the role:

Required skills:

• 12+ years of professional experience in software engineers and building applications/systems
• 2+ years of hands-on experience in how LLMs work & Generative AI (LLM) techniques particularly multi-agent systems.
• Expert proficiency in programming skills in Python, Langgraph and SQL is a must.
• Expert in architecting GenAI applications/systems using various frameworks & cloud services
• Expert proficiency in using AI tools like claude code, codex, cursor, windsurf and the likes.
• Expert proficiency in AI observability & evaluation tools like Langsmith, Langfuse or similar
• Good proficiency in using various cloud services from Azure, Google Cloud Platform, or AWS for building the GenAI applications
• Experience in driving the engineering team toward a technical roadmap.
• Excellent communication skills to effectively collaborate with business SMEs

Roles & Responsibilities:

• Solutioning & Lead
  • Build the technical roadmap given a business requirement and own the delivery of the same.
  • Lead the engineering team toward a technical roadmap and ensure timely execution of the roadmap to achieve customer satisfaction.
  • Design robust multi-agent architectures including supervisor-router patterns with dynamic sub-agent routing and stopping conditions
  • Mentoring and guidance: Provide technical leadership and knowledge-sharing to the engineering team, fostering best practices in machine learning and large language model development.
• Hands-on skills
  • Develop LLM-based solutions: Lead the design, training, fine-tuning, and deployment of large language models, leveraging techniques like retrieval-augmented generation (RAG) and multi-agent based architectures.
  • Build and maintain agent evaluation pipelines, including offline eval datasets, LLM-as-judge, and CI-integrated eval runs
  • Codebase ownership: Build & maintain high-quality, efficient code in Python (using frameworks like LangChain/LangGraph) and SQL, focusing on reusable components, scalability, and performance best practices.
  • Cloud integration: Deployment of GenAI applications on cloud platforms (Azure, Google Cloud Platform, or AWS), optimizing resource usage and ensuring robust CI/CD processes..