Senior Python Backend Engineer

Job Description:

In this role, you will architect and maintain scalable backend systems that orchestrate communication across internal services, external APIs, and AI models. You will design robust integration layers, manage structured and unstructured data flows, and ensure reliable, secure, and efficient LLM-powered interactions across our product ecosystem.

You will collaborate closely with AI engineers and product teams to productionize LLM capabilities—implementing prompt orchestration, model routing, evaluation frameworks, and performance optimization strategies. Your work will directly power intelligent features embedded across multiple applications, ensuring high availability, observability, and maintainability of AI-driven services.

This role requires strong backend architecture expertise, experience integrating AI/LLM systems into production environments, and a solid understanding of distributed systems, APIs, and service-to-service communication patterns.

Key Responsibilities:

Design and implement scalable backend services that enable reliable interactions between internal applications and LLM interfaces (internal and external).

Build and maintain robust API layers and service orchestration components to manage prompts, context injection, and model routing in both synchronous and asynchronous environments.

Improve performance, latency, and cost-efficiency of LLM calls and AI-driven services.

Implement comprehensive monitoring, logging, tracing, and observability for AI-integrated systems.

Contribute to DevOps and CI/CD practices to ensure safe, repeatable deployment of backend and AI-enabled services.

Collaborate closely with AI/ML engineers and product teams to translate model capabilities into production-ready backend solutions.

Evaluate and integrate emerging LLM technologies, mentor engineers, and clearly communicate architectural decisions to technical and non-technical stakeholders.

Qualifications:

Bachelor's or Master's degree in Computer Science, Software Engineering, or a related technical field.

6-7 years of experience in Software, Data, or ML engineering roles

Strong problem-solving skills, proficiency in Python.

Understanding of LLMs, model architectures, MCP, and experience building scalable, reliable AI systems.

Strong understanding of container orchestration, scaling strategies, networking and resource management in Kubernetes clusters.

Familiarity with CI/CD tools (e.g., GitHub Actions)

Ideal Candidate

This role is well-suited for someone with a strong foundation in backend engineering, distributed systems, or AI-integrated application development, and a willingness to deepen their expertise across system architecture and LLM-driven solutions as the platform evolves.

We are looking for a language-agnostic problem solver who understands how to design reliable, scalable services and is passionate about building robust systems that integrate AI capabilities into real-world applications. Experience with LLMs, service orchestration, or retrieval-based systems is highly valued—but we also welcome candidates who are eager to grow into these areas.

If you thrive at the intersection of backend architecture and applied AI, enjoy enabling multiple services to interact seamlessly with intelligent systems, and care about performance, reliability, and maintainability, this role is for you—even if you don’t meet every listed requirement.

Come and join our #ParserCommunity. 

Follow us on Linkedin