Senior Python Engineer (LLM/RAG)

Spsoft is looking for an experienced Python developer with strong knowledge of FastAPI or similar frameworks and hands-on experience integrating large language models (LLMs) into web applications and services to participate in the development of a scalable and fully customizable AI voice Agents platform (currently in Beta) that can be adapted to specific client needs and integrated into existing apps.

The ideal candidate has a product-thinking and product-design mindset. You should be proactive and think ahead rather than wait for the next task in the pipeline. It is mandatory to be able and willing to work in a fast and intense startup environment for 200+ hours per month. In return, you will be eligible for equity and benefit from a successful startup exit.

If you’re looking for a relaxed job at a moderate pace – please do not apply.

Duties and responsibilities

• Design, develop, and maintain web applications using FastAPI or similar frameworks.
• Integrate LLMs (OpenAI, GPT, etc.) into applications to create AI-powered features.
• Optimize applications for performance, security, and scalability.
• Write clean, maintainable, and well-documented code.
• Troubleshoot and debug issues to improve the performance of applications.
• Stay updated with the latest trends and best practices in Python development and AI integration.

Required skills and experience

• Strong experience in Python development (4+ years).
• Proven expertise in FastAPI or similar frameworks.
• Hands-on experience integrating Large Language Models (e.g., GPT, LLAMA) into applications.
• Familiarity with RESTful API design and microservices architecture.
• Experience with Docker, Kubernetes, or similar container orchestration tools.
• Knowledge of database technologies such as PostgreSQL or MongoDB.
• Proficient with version control tools such as Git.
• Excellent problem-solving skills and attention to detail.
• Ability to work independently as well as in a collaborative team environment.

Will be a plus:

• Experience with cloud platforms (AWS, Azure, GCP).
• Experience with asynchronous programming (e.g., asyncio).
• Knowledge of CI/CD pipelines and DevOps practices.
• Experience with graph databases (e.g., Neo4j).
• Understanding of Retrieval-Augmented Generation (RAG) applications.
• Experience with STT and TTS models, like Deepgram, Whisper, and ElevenLabs.

What’s in it for you

• You will be working as a part of our engineering team as an individual contributor, meaning that a lot will depend on you.
• You will have to learn how to co-create and co-design the product, not just write code based on the pre-digested specifications written for you by somebody else.
• As an end-to-end co-product designer/software engineer, you will learn to deliver more value.
• You will develop much faster than the fractional role at one of the big “galleys.”