Volga Partners

Software Development Engineer - AI / LLM Systems (Python Backend)

  • Volga Partners
  • Remote India
Apply Now

Job Description

Company: Volga Partners 
Location: Fully Remote (Occasional office visits 1–2 times/year) 
Compensation: ₹23–₹30 LPA (based on experience) 
Job Type: Full-time 
Start Date: Urgently hiring — must be available to start within 1–2 weeks 
Work Hours: 8 AM – 5 PM IST or 9 AM – 6 PM IST 
(Collaboration with USA Pacific Time teams) 

 

About the Role 

Volga Partners is looking for a skilled Software Development Engineer with strong expertise in Python backend systems and AI/LLM applications. 

In this role, you will build and maintain production-grade AI-powered systems, integrating large language models into real-world workflows. You will work across backend services, orchestration layers, and data pipelines—ensuring that AI features are reliable, scalable, and performant. 

This is a hands-on engineering role requiring strong problem-solving, system design, and the ability to operate in fast-evolving AI environments. 

 

Key Responsibilities 

  • Build and maintain backend services and internal tools in Python for AI-powered applications.  
  • Integrate LLM APIs into production workflows, including prompt handling, response processing, validation, and retries.  
  • Design and implement scalable REST APIs, async workflows, and background job systems.  
  • Maintain and enhance components of a multi-language codebase (C#/C++, Python, web technologies) where applicable.  
  • Work with structured and unstructured data to prepare inputs, transform outputs, and support downstream systems.  
  • Develop systems for prompt management, model routing, response validation, and failure handling.  
  • Debug complex issues across backend logic, API integrations, and distributed services.  
  • Monitor system performance using telemetry tools and proactively identify and resolve bottlenecks.  
  • Automate recurring workflows related to data processing, evaluation, and reporting.  
  • Collaborate with cross-functional teams to turn ambiguous product ideas into production-ready features.  
  • Contribute to architecture decisions around scalability, performance, and safe use of AI systems.  
  • Write clean, testable, and maintainable code while helping establish engineering best practices for AI systems.  

 

What You Bring 

Education 

  • Bachelor’s degree in Computer Science or a related field.  

Experience 

  • 3+ years of professional experience in backend or systems engineering.  
  • Strong experience in Python development for production systems.  
  • Experience integrating LLM APIs or AI-driven services into real applications.  
  • Proven ability to work within large codebases and collaborative environments.  

 

Technical Skillset 

Core Skills 

  • Python (strong), backend system design, API development  
  • Async workflows, job queues, and service orchestration  
  • Debugging across APIs, services, and data pipelines  

Languages 

  • Python, C#, C/C++, JavaScript/TypeScript, SQL  

Frameworks & Libraries 

  • .NET Web API, ASP.NET (MVC & WebForms), Entity Framework  
  • React, Bootstrap, Ajax  
  • Testing frameworks (xUnit or similar)  

AI / LLM Systems 

  • Prompt design, response parsing, and guardrails  
  • Model integration patterns and failure handling  
  • Understanding of LLM limitations and production constraints  

Tools & Platforms 

  • Azure DevOps, Git, Docker, Terraform  
  • SQL Server or similar databases  
  • Elastic Stack, Postman, Swagger  
  • AWS or Azure cloud environments  

Architecture 

  • Microservices, distributed systems, modular architectures  

Operating Systems 

  • Windows, Linux  

Build Tools 

  • Make, Ninja (preferred)  

 

Nice to Have 

  • Experience with RAG, embeddings, vector databases, or retrieval systems  
  • Familiarity with agent workflows or multi-step orchestration  
  • Experience with model monitoring, prompt versioning, or evaluation systems  
  • Understanding of AI safety, privacy, and secure data handling  
  • Exposure to cloud-native deployments and scalable infrastructure  

 

Why Join Us 

  •  Remote-first culture with minimal in-person requirements  
  •  Work with global teams on cutting-edge AI systems  
  •  Opportunity to build real-world LLM applications at scale  
  •  High ownership, fast-moving environment with strong growth potential