AI Engineer

Soul Ai; Hyderabad; On-site; INR 1,200,000 - 2,400,000; Full time

Job summary

Soul Ai in Hyderabad, India is seeking an AI/ML backend engineer to design and build production-grade pipelines and autonomous coding agents. You will develop code intelligence systems, integrate LLMs, and scale backend components in Python.

You will work with Docker-based environments, vector retrieval, and rigorous testing to ensure reliability and performance in large repositories. This role emphasizes high-quality software architecture and proactive code reviews.

Qualifications

• 2+ years of experience in AI/ML engineering, backend systems, or developer tooling.
• Strong Python expertise, including concurrency and performance-oriented programming.
• Hands-on experience with coding agents and autonomous reasoning loops.
• Proficiency in AST/CST parsing (Tree-sitter, LibCST) and large codebase indexing.
• Experience building RAG pipelines using vector databases such as ChromaDB.
• Extensive experience with Docker for containerizing ML systems.
• Strong testing discipline with Pytest, PEP 8 compliance, and type hinting.
• Proven ability to conduct rigorous PR reviews and identify issues.

Responsibilities

• Design and build asynchronous, production-grade AI/ML pipelines with autonomous coding agents.
• Develop code intelligence systems using AST/CST parsing and vector-based retrieval over large repositories.
• Integrate LLMs and agent frameworks to enable autonomous coding and repository-level reasoning.
• Build scalable, high-throughput backend systems in Python.
• Containerize and manage ML environments using Docker and multi-container setups.
• Write and maintain comprehensive automated tests to ensure reliability and correctness.
• Enforce high standards for code quality, abstraction, and maintainability.

Skills

Python concurrency

Performance-oriented programming

Testing with Pytest

Code reviews

Autonomous reasoning loops

Tools

Docker

Tree-sitter

LibCST

ChromaDB

Cursor CLI

OpenHands

Aider

Job description

Role Responsibilities:

• Design and build asynchronous, production-grade AI/ML pipelines integrating autonomous coding agents
• Develop code intelligence systems using AST/CST parsing and vector-based retrieval over large repositories
• Integrate LLMs and agent frameworks to enable autonomous coding and repository-level reasoning
• Build scalable, high-throughput backend systems in Python
• Containerize and manage complex ML environments using Docker and multi-container setups
• Write and maintain comprehensive automated tests to ensure reliability and correctness
• Enforce high standards for code quality, abstraction, and maintainability

Must-Have Qualifications

• 2+ years of experience in AI/ML engineering, backend systems, or developer tooling
• Strong Python expertise, including concurrency and performance-oriented programming
• Hands-on experience with coding agents (e g , Cursor CLI, OpenHands, Aider) and autonomous reasoning loops
• Proficiency in AST/CST parsing (Tree-sitter, LibCST) and large codebase indexing
• Experience building RAG pipelines using vector databases such as ChromaDB
• Extensive experience with Docker for containerizing and managing ML systems
• Strong testing discipline with Pytest, PEP 8 compliance, and type hinting
• Proven ability to conduct rigorous PR reviews and identify architectural, security, and performance issues
• Experience with prompt engineering and agent optimization