Lead AI Engineer (Agentic AI, LangChain, Python) (в архиве)

About the Project
Fuel card sales in the U.S. (all sales are conducted within the United States).
Project launch: March 2024.
Part of a logistics group: The project is a division of a U.S. trucking logistics group, which is the market leader in Uzbekistan.
The company is a registered IT Park resident with offices in Tashkent (two offices), Chicago, and Orlando.

Purpose of the Role
To build the internal agentic AI architecture from scratch — from designing LLM agents and pipelines to setting up production infrastructure. The main objective is to automate and optimize internal processes using advanced LLM-based tools.

Key Responsibilities

• Design and implement internal AI-agent architecture from the ground up.

• Utilize OpenAI API, LangChain (or similar frameworks), and external tools (SQL, APIs, files).

• Develop systems for planning, memory, query processing, and action generation.

• Integrate agents with internal data sources (databases, Google Docs, files, CRM, etc.).

• Deploy solutions into production ensuring scalability and reliability.

• Establish documentation, standards, and a foundation for scaling AI initiatives.

Requirements

• 4+ years of hands-on development experience with Python.

• 1+ years of experience with LLM infrastructure (LangChain, OpenAI API, RAG, etc.).

• Proven experience designing and implementing agentic approaches (or similar pipelines).

• Strong skills in working with APIs, SQL, file sources, and knowledge bases.

• Solid understanding of LLM architecture, memory, tool usage, and reasoning principles.

• Experience in deployment: Docker, CI/CD, and basic DevOps practices.

• Ability to work independently and build infrastructure from scratch.

• Experience in documenting and setting up tech stacks for scaling.

Nice to Have

• Experience building RAG systems (retrieval-augmented generation).

• Knowledge of vector databases (FAISS, Weaviate, Pinecone, etc.).

• Hands-on work with LangGraph, CrewAI, AutoGPT, or similar frameworks.

• Production-level experience integrating PDF, CSV, email streams, calendars, and other data sources.

Tools and Technologies
Python, LangChain, OpenAI API
SQL, REST APIs, Docker, Git
Vector databases (as required)
Airflow/FastAPI (optional)

Conditions

• Compensation: discussed individually, depending on competencies.

• Direct access to top management — your ideas will be heard.

• Work schedule: 5/2, following the U.S. production calendar for holidays and weekends.

• Hybrid work format.

• Relocation candidates are also considered.