AI/LLM Engineer (Agentic AI & Generative AI)

Overview:

Job Title: AI/LLM Engineer (Agentic AI & Generative AI)

Location: New York, NY

Job Type: Full-Time

Experience: 8-10 Years

Job Summary

We are seeking an experienced AI/LLM Engineer to design, develop, and deploy enterprise-grade Generative AI and Agentic AI solutions. The ideal candidate will have strong expertise in Python, LLM orchestration, autonomous agents, RAG architectures, and modern AI frameworks such as LangChain and LangGraph.

This role will focus on building intelligent agent-based systems capable of reasoning, planning, and executing tasks autonomously while integrating seamlessly with enterprise data platforms and applications.

Required Skills

AI & Agentic AI

• Strong hands-on experience building AI-powered applications using:
  • LangChain
  • LangGraph
  • Agentic AI Frameworks
  • Multi-Agent Architectures
• Experience implementing:
  • ReAct (Reasoning + Acting)
  • Tool Calling
  • Agent Orchestration
  • Workflow Automation
  • Autonomous Decision-Making Systems

Large Language Models (LLMs)

• Experience with:
  • OpenAI
  • Anthropic Claude
  • Gemini
  • Llama Models
• Strong understanding of:
  • Prompt Engineering
  • Context Management
  • Memory Architectures
  • Model Evaluation
  • LLM Optimization

MCP & AI Orchestration

• Hands-on experience implementing:
  • Model Context Protocol (MCP)
  • Memory Management
  • Context Windows
  • Tool Integration Frameworks
  • Retrieval and Reasoning Pipelines

Software Engineering

• Expert-level Python development
• Strong experience with:
  • Async Programming
  • REST APIs
  • Microservices Architecture
  • Distributed Systems
• Experience developing production-grade AI platforms

Data Platforms & Integration

• Experience working with:
  • Snowflake
  • Databricks
  • Lakehouse Architectures
  • Enterprise Data Pipelines
• Understanding of:
  • Data Engineering
  • Data Integration
  • Data Governance

Responsible AI & Guardrails

• Experience implementing:
  • AI Safety Controls
  • Guardrails
  • Content Filtering
  • Security Controls
  • Failure Recovery Mechanisms
• Knowledge of Responsible AI principles and governance frameworks

Key Responsibilities

Agent Development

• Design and build intelligent AI agents using modern agent frameworks
• Implement reasoning, planning, memory, and execution capabilities
• Develop multi-step autonomous workflows and agent orchestration patterns

LLM Engineering

• Build and optimize LLM-powered applications
• Implement tool-calling, memory management, and context-aware systems
• Improve model performance, reliability, and response quality

Platform Engineering

• Develop scalable APIs and microservices for AI applications
• Design highly available and production-ready AI systems
• Optimize performance, latency, and scalability

Data Integration

• Integrate AI solutions with enterprise data platforms and pipelines
• Work with Snowflake, Databricks, and Lakehouse environments
• Enable secure and efficient access to enterprise knowledge sources

Governance & Reliability

• Implement AI guardrails, observability, and monitoring
• Ensure compliance with Responsible AI practices
• Handle edge cases, failure scenarios, and model safety requirements

Preferred Qualifications

• Experience with:
  • RAG (Retrieval-Augmented Generation)
  • Vector Databases (Pinecone, Weaviate, Chroma, Qdrant)
  • Embeddings
  • Semantic Search
  • AI Observability Platforms
• Cloud experience with:
  • AWS
  • Azure
  • GCP
• Experience with Docker, Kubernetes, and CI/CD pipelines
• Exposure to MLOps and AI platform engineering