Senior LLM/RAG Engineer (Legacy Modernization)
Qualifications
Experience Level: Senior Level
- Deep understanding of Abstract Syntax Trees (AST) and experience in parsing or transforming code programmatically.Modernization Knowledge: Familiarity with code migration processes
- microservices architecture
- and cloud-native design patterns.Tools & Version Control: Expert-level knowledge of Git for managing generated code and collaborative development.Soft Skills: A proactive nature with strong communication skills
- essential for navigating the ambiguity of a POC environment and working with distributed global teams.
- We offer Opportunity to work on bleeding-edge projectsWork with a highly motivated and dedicated teamCompetitive salaryFlexible scheduleBenefits package - medical insurance
- sportsCorporate social eventsProfessional development opportunitiesWell-equipped office
- About UsGrid Dynamics (NASDAQ: GDYN) is a leading provider of technology consulting
- platform and product engineering
- and advanced analytics services. Fusing technical vision with business acumen
- we solve the most pressing technical challenges and enable positive business outcomes for enterprise companies undergoing business transformation. A key differentiator for Grid Dynamics is our 8 years of experience and leadership in enterprise AI
Full Job Description
The LLM/RAG Engineer will be a key player in a high-profile modernization project, upgrading a legacy RPG/IBM i-based Dealer Management System (DMS) to a modern, cloud-native Java architecture. During this Proof of Concept (POC) phase, you will focus on CodeRAG (Retrieval-Augmented Generation for code) and Abstract Syntax Tree (AST) techniques. Your main goal is to automate the parsing, transformation, and migration of legacy business logic into modern microservices. You will work at the intersection of Generative AI and legacy system modernization, ensuring accurate, performant, and architecturally aligned automated code generation.
Responsibilities
- Code Transformation & Analysis: Use AST techniques to parse legacy RPG code and convert it into structured formats for automated migration.
- RAG Implementation: Design and maintain RAG pipelines using AWS Bedrock and Vector Databases to provide LLMs with high-fidelity context.
- Data Preprocessing: Clean, structure, and enrich metadata from legacy systems.
- Iterative Validation: Rigorously validate and correct AI-generated code.
- Legacy Integration: Collaborate with code analysis tools.
- Collaboration & Documentation: Work with global teams, documenting complex business logic.
- Quality Assurance: Adhere to architectural specifications.
Requirements
- Minimum 4–8 years of software engineering experience, with a focus on AI/ML or Backend development.
- Experience with advanced LLMs (e.g., Claude 3.5/3.7/4) and building RAG pipelines.
- Strong proficiency in Python.
- Experience with AWS Bedrock.
- Experience with Vector Databases such as Milvus or Pinecone.
- Deep understanding of Abstract Syntax Trees (AST).
- Familiarity with code migration, microservices architecture, and cloud-native design patterns.
- Expert-level knowledge of Git.
- Strong communication skills.
We Offer
- Opportunity to work on cutting-edge projects
- Work with a highly motivated and dedicated team
- Competitive salary
- Flexible schedule
- Benefits package - medical insurance, sports
- Corporate social events
- Professional development opportunities
- Well-equipped office
Company
Grid Dynamics
Grid Dynamics (Nasdaq: GDYN) is an AI-first digital engineering services and technology consulting company. Based in Silicon Valley, California, and with a global footprint, we transform Fortune 1000 ...