Java Fullstack Engineer with AI

Job Title: Agent Engineer Location: New York, NY ( Hybrid) Duration: 12 Months Work Hours: 40 hrs/week

Job Summary: The Agent Engineer designs, develops, and iterates on AI agents that can reason, plan, and execute multi-step tasks autonomously. This is the core builder role of the agentic technology stack combining software engineering, LLM expertise, and systems thinking to create reliable agents that integrate seamlessly with enterprise tools, APIs, and data sources.

Responsibilities:

• Design and implement AI agents with well-defined goals, tools, memory systems, and reasoning loops
• Build agent tooling integrations - connecting agents to APIs, databases, internal services, and external platforms via function calling or MCP
• Develop and maintain agent memory architectures (short-term, long-term, episodic) for context persistence across sessions
• Implement robust error handling, retry logic, and fallback behaviors to ensure agent reliability in edge cases
• Write comprehensive unit and integration tests for agent behaviors, including adversarial test cases
• Collaborate with Product Managers to translate business requirements into agent capabilities and constraints
• Optimize agent performance - reducing token usage, latency, and cost without sacrificing output quality
• Participate in agent evaluation cycles, reviewing outputs and incorporating feedback into agent design
• Document agent architectures, tool schemas, and design decisions for cross-team visibility
• Stay current with the rapidly evolving agentic AI ecosystem (frameworks, models, protocols, best practices)

Required Qualifications:

• 3+ years of software engineering experience; 1+ years working with LLMs or AI agents
• Strong proficiency in Python; familiarity with TypeScript/JavaScript a plus
• Experience with at least one agentic framework: LangChain, Lang Graph, Crew AI, AutoGen, or custom implementations
• Solid understanding of LLM capabilities and limitations (context windows, tool use, structured outputs, hallucination patterns)
• Experience with REST APIs, vector databases (Pinecone, Weaviate, Chroma), and data retrieval systems
• Familiarity with prompt engineering principles and context management strategies
• Understanding of async programming, event-driven architectures, and distributed systems
• Strong debugging skills and comfort with ambiguous, non-deterministic systems

Preferred Skills:

• Experience fine-tuning LLMs or working with model APIs (Anthropic, OpenAI, Mistral, local models)
• Background in RAG (Retrieval-Augmented Generation) architecture design
• Contributions to open-source AI/agent frameworks

For applications and inquiries, contact: [email protected]