Lead AI Software Engineer (Python)

EPAM Systems; United States; Remote; USD 170,000 - 230,000; Full time

Benefits offered by this job

Vacation and sick leave

Family medical insurance

Life event support

Mental health discounts

Code language training for employees'/

Job summary

EPAM Systems is seeking a seasoned Lead AI Software Engineer to lead the design and development of agentic and multi-agent systems at scale. You will drive production-grade AI applications using LangChain and LangGraph, while collaborating with cross-functional teams to advance RAG evaluation and data storage strategies.

The role emphasizes extensive Python development, cloud familiarity, and hands-on experience with state-of-the-art AI platforms.

Qualifications

• Proficient in Python with strong engineering practices.
• Experience with LangChain and graph frameworks is essential.
• Understanding of cloud platforms and data science concepts.

Responsibilities

• Support the design of agentic AI systems and multi-agent architectures at scale.
• Develop production-grade AI applications using LangChain and LangGraph.
• Contribute to retrieval-augmented generation (RAG) evaluation methods.
• Build and maintain vector databases for AI data storage and retrieval.
• Apply data science techniques to boost AI system performance.
• Collaborate with cross-functional teams to integrate AI solutions.
• Document system designs and development processes.
• Deploy and monitor AI applications and troubleshoot bottlenecks.

Skills

Python programming

LangChain

LangGraph

Cloud platforms

Data science methodologies

Team leadership

Job description

We are seeking a seasoned Lead AI Software Engineer to join our software, system and test engineering group. You will lead the design and development of agentic and multi-agent systems at scale using the LangChain and LangGraph frameworks, with a focus on scalable, production-grade applications. Join us to contribute to advanced AI solutions for our clients.

Professional Growth and Technical Upskilling:

We invest heavily in our engineering culture and provide the infrastructure you need to stay at the forefront of artificial intelligence.

Advanced AI Ecosystems:

Gain hands-on experience building, orchestrating, and scaling AI agents using EPAM’s proprietary platforms EliteA and CodeMie, alongside our open-source AI orchestration platform DIAL, with complimentary access to leading LLMs.

Specialized GenAI Training:

Access dedicated internal learning paths focused on advanced prompt engineering, agentic system design, RAG architectures, and AI evaluation frameworks.

Continuous Learning:

Enjoy unlimited access to the LinkedIn Learning library (16,000+ courses) and our internal e-learning portal with specialized technical training.

Cloud AI Certifications:

Advance your expertise with company-sponsored training and certification vouchers for industry-recognized credentials, including Anthropic, AWS, Azure, GCP, and Databricks.

Engineering Excellence (EngX):

Elevate your code quality through our EngX programs, covering advanced Python, MLOps, clean architecture, and ADLC best practices.

Technical Guilds and Hackathons:

Join our active AI communities. Participate in architectural deep-dives, internal TechTalks, and global GenAI hackathons to prototype solutions using cutting-edge models.

What we offer

• Vacation and sick leave (including a sick leave without a medical certificate)
• A wide range of Voluntary Medical Insurance programs providing both medical treatment and various preventive options (including sports activities)
• Medical insurance for family members at corporate rates
• Company support during significant life events (childbirth or adoption, marriage, etc.)
• Support for psychological comfort: discounts on services from mental health specialists or coaches, thematic training E-kids program — a free programming language training program for EPAMers’ children

Responsibilities

• Support the design of agentic AI systems and multi-agent systems at scale
• Assist in developing production-grade AI applications with LangChain and LangGraph frameworks
• Contribute to implementing retrieval-augmented generation (RAG) evaluation methods
• Build and maintain vector databases for AI data storage and retrieval
• Apply data science techniques to improve AI system performance
• Collaborate with cross-functional teams to integrate AI solutions
• Develop scalable and efficient AI system architectures
• Troubleshoot and resolve system issues and bottlenecks
• Acquire knowledge about AI and machine learning advancements
• Document system designs and development processes
• Participate in code reviews and follow best practices
• Use Cloud AI Native tools
• Deploy and monitor AI applications

Requirements

• Interest in designing and developing agentic AI systems and multi-agent systems
• Programming skills in Python with 6+ years of experience
• Familiarity with LangChain and graph frameworks such as LangGraph
• Understanding of cloud platforms
• Background in data science or data engineering methodologies