Python Developer Gen AI - remote

Senovo - IT are looking for a Senior AI Engineer with strong Python and software engineering experience to design and build production-grade GenAI applications.

This role focuses on integrating LLM capabilities, agentic workflows, and Retrieval-Augmented Generation (RAG) into enterprise systems.

The position is engineering-focused, not a research role, and requires hands-on experience building scalable AI services.

You will work closely with product teams and engineers to deliver AI-driven solutions across enterprise platforms, ensuring reliability, performance, and security.

Key Responsibilities

• Design, build, and operate LLM-powered applications and AI services.

• Implement agentic workflows and orchestration systems integrating tools, APIs, and enterprise data sources.

• Develop and optimize RAG pipelines, including ingestion, chunking, embeddings, retrieval strategies, and evaluation.

• Integrate AI solutions with existing enterprise platforms and backend services via APIs.

• Design function/tool calling interfaces and structured outputs for AI systems.

• Build scalable AI microservices and event-driven architectures.

• Ensure production-grade reliability through monitoring, logging, testing, and performance optimization.

• Collaborate with engineering teams to mentor developers and improve AI engineering practices.

Required Skills & Experience

Core Engineering

• 5+ years of software engineering experience building production systems.

• Strong experience with Python (preferred for AI/ML systems).

• Experience building and integrating REST APIs.

• Understanding of distributed systems concepts (async processing, rate limits, retries, caching).

• Strong SQL/database fundamentals.

AI / GenAI Engineering

• Experience building LLM-powered applications.

• Hands-on experience with RAG architectures.

• Experience designing agentic AI workflows.

• Familiarity with frameworks such as:

  • LangChain

  • LangGraph

  • Microsoft Semantic Kernel

• Experience with prompt engineering, tool/function calling, and structured outputs.

• Understanding of LLM evaluation, hallucination mitigation, and guardrails.

If interested and available please share your CV for an immiediate consideration.