AI/LLM Engineer

Acestack; New York (NY); On-site; USD 120,000 - 160,000; Full time

Benefits offered by this job

Health insurance

Job summary

Acestack in New York, NY seeks an AI/LLM Engineer to design, develop, and deploy agent-based systems that reason, plan, and execute tasks autonomously.

The role emphasizes strong Python engineering, experience with agent frameworks, LLM architectures, and scalable, production-ready AI apps across data platforms and cloud environments.

Qualifications

• Proven experience building AI/LLM powered applications.
• Hands-on Python software development for AI systems.
• Experience with agent-based workflows and orchestration.
• Familiarity with LangChain, LangGraph, or similar frameworks.
• Understanding of RAG, embeddings, vector databases, and search.

Responsibilities

• Design, develop, and deploy agent-based systems with reasoning and autonomous execution.
• Integrate LLMs into enterprise apps via OpenAI/Anthropic/Google APIs.
• Develop memory, tool usage, and context management capabilities.
• Build Python applications and REST APIs with scalable architecture.
• Deploy AI solutions in cloud environments and monitor production systems.

Skills

Python engineering

LLM applications

Agent frameworks

LangChain

ReAct

MCP

REST APIs

Tool integration

Testing & debugging

Git

Tools

LangGraph

OpenAI API

Anthropic API

Google Gemini

Docker

Kubernetes

CI/CD

Job description

Job Title: AI/LLM Engineer

Location: New York, NY

Full-Time

Job Description

We are looking for a highly skilled AI/LLM Engineer to design, develop, and deploy intelligent agent-based systems capable of reasoning, planning, and executing tasks autonomously. The ideal candidate will have strong Python engineering skills, hands-on experience with modern AI agent frameworks, and a solid understanding of LLM architectures, data platforms, and scalable software systems.

The candidate will build advanced AI solutions using Large Language Models (LLMs), agentic workflows, tool integration, and context management to deliver reliable, scalable, and production-ready AI applications.

Key Responsibilities

1. Agent & AI System Development

• Design, develop, and deploy agent-based systems using frameworks such as LangChain, LangGraph, or similar technologies.
• Build intelligent components capable of reasoning, planning, decision-making, and autonomous task execution.
• Implement advanced agentic patterns, including ReAct (Reasoning + Acting), multi-step reasoning, and workflow orchestration.
• Develop multi-agent systems to coordinate complex tasks and business processes.

2. LLM Capabilities & Enhancements

• Integrate LLMs into enterprise applications using APIs from OpenAI, Anthropic, Google, or similar providers.
• Develop memory, tool usage, and context management capabilities, including Model Context Protocol (MCP).
• Implement tool calling, prompt chaining, and orchestration of LLM-powered workflows.
• Optimize prompts and model interactions for accuracy, reliability, latency, and cost.
• Implement appropriate evaluation and validation mechanisms to improve LLM output quality.

3. Python Engineering & Application Development

• Develop clean, maintainable, and scalable Python applications for AI-driven solutions.
• Build REST APIs and integrate AI agents with databases, enterprise systems, and external services.
• Implement asynchronous processing, error handling, logging, and testing for production-grade AI applications.
• Follow software engineering best practices, including version control, code reviews, and automated testing.

4. Data Platforms & Scalable Architecture

• Integrate AI agents with structured and unstructured data sources.
• Work with vector databases, embeddings, semantic search, and Retrieval-Augmented Generation (RAG).
• Design scalable architectures for LLM applications, including data ingestion, retrieval, and processing pipelines.
• Apply security, access control, and responsible AI practices when handling enterprise data.

5. Deployment & Production Support

• Deploy and maintain AI/LLM applications in cloud environments such as AWS, Azure, or GCP.
• Use Docker, Kubernetes, and CI/CD pipelines where applicable.
• Monitor agent performance, troubleshoot production issues, and continuously improve system reliability.
• Collaborate with data engineers, software developers, product managers, and business stakeholders.

Required Technical Skills

• Strong hands-on experience with Python and software application development.
• Experience building LLM applications and agent-based systems.
• Proficiency in LangChain, LangGraph, or comparable agent frameworks.
• Understanding of agentic AI patterns, including ReAct, planning, reasoning, and autonomous execution.
• Experience with MCP (Model Context Protocol), tool calling, memory, and context management.
• Experience integrating LLM APIs such as OpenAI, Anthropic, or Google Gemini.
• Knowledge of RAG, embeddings, vector databases, and semantic search.
• Experience developing APIs and integrating AI applications with external systems.
• Understanding of scalable application architecture, testing, and debugging.
• Familiarity with Git and modern software development practices.

Preferred Qualifications

• Experience with multi-agent orchestration and advanced agentic workflows.
• Experience with cloud platforms such as AWS, Azure, or GCP.
• Knowledge of Docker, Kubernetes, CI/CD, and production deployment.
• Experience with LLM evaluation, observability, guardrails, and prompt optimization.
• Familiarity with SQL, NoSQL databases, and distributed data processing.
• Experience deploying enterprise-grade AI solutions in production environment