Role: AI Developer
Experience: 10 years
Location: NYC
Required Skills:
Agentic AI Development
• Design and build AI agents capable of reasoning, planning, and executing tasks autonomously
• Develop modular agent components (planners, executors, evaluators, orchestrators)
• Implement multi-step workflows combining LLMs with external tools and APIs
Framework & System Design
• Build and extend agent frameworks for orchestration, chaining, and decision-making
• Develop memory systems (short-term and long-term) to improve agent context retention
• Implement tool-use capabilities, enabling agents to interact with databases, APIs, and enterprise systems
RAG & Knowledge Systems
• Design and implement Retrieval-Augmented Generation (RAG) pipelines
• Work with embeddings and vector databases to enable semantic search and contextual reasoning
• Optimize document ingestion, chunking, indexing, and retrieval strategies
Collaboration & Integration
• Collaborate with prompt engineers to refine prompts, evaluation strategies, and agent behaviors
• Work with cloud and platform teams to deploy scalable AI services
• Integrate AI solutions into enterprise workflows and applications
Technical Skills
• Strong programming expertise in Python
• Hands-on experience with LLMs and agentic frameworks (e.g., LangChain, Semantic Kernel, or similar)
• Solid understanding of:
o Embeddings and vector databases (e.g., Pinecone, FAISS, Azure AI Search)
o RAG architectures and pipelines
o Prompt engineering and evaluation techniques
Cloud & Infrastructure
• Good understanding of the Azure cloud ecosystem, including:
o Azure OpenAI Service
o Azure Functions / App Services
o Azure AI Search or equivalent services
• Experience deploying scalable AI/ML solutions in cloud environments
System Thinking
• Ability to design modular, scalable, and reusable AI components
• Understanding of state management, memory architectures, and agent orchestration
• Strong problem-solving and analytical thinking
• Ability to work in a cross-functional, fast-paced environment
• Clear communication skills to collaborate with both technical and non-technical stakeholders
Preferred Qualifications/ Skills
• Experience building multi-agent systems
• Familiarity with evaluation frameworks for LLMs (hallucination detection, response quality, etc.)
• Exposure to MLOps / LLMOps practices
• Knowledge of API integrations and microservices architecture
• Experience in enterprise AI deployments (banking, risk, or financial services preferred)
• Contributions to open-source AI/LLM projects
• Familiarity with agent evaluation benchmarks and guardrails
Never miss an opportunity! Create an alert based on the job you applied for.
