Senior Python / LLM Developer

At Celestify, we build smart web, mobile, and AI-powered apps that help startups and businesses solve real problems. We're growing our small, fully-remote team and looking for a Senior Python Developer to join us in supporting an ambitious client building a cutting-edge AI assistant to transform regulatory review in the pharmaceutical industry.

You will be building scalable Python systems, designing robust RAG pipelines, optimising performance and shaping the technical foundations of an LLM-powered product in an agile environment. You'll work closely with the founding team and a high-performing internal dev team to ship production-grade AI features, end to end.

This role requires close collaboration with the client team, clear written and verbal communication, and the ability to work independently from well-scoped GitHub issues. If you're a thoughtful engineer who thrives on problem-solving, communication, and getting things done, you'll fit right in.

Tech stack

• Backend: Python, FastAPI, PostgreSQL
• Integration: LlamaIndex, Node.js
• LLMs: OpenAI / Gemini / fine-tuned models
• Task queue: Celery, Redis
• Infra: Docker, Kubernetes, Azure, Vercel
• Monitoring: Prometheus, ClickHouse

What you bring – Must haves

• Strong Python development experience with focus on performance and clean architecture
• Proven experience working with LLM integration frameworks like LlamaIndex, Langchain etc.
• Deep understanding of RAG pipelines and document retrieval systems
• Strong PostgreSQL skills, including data modelling and query optimisation
• Solid fundamentals in algorithms, memory management, and system design
• Experience designing and building APIs with FastAPI (or similar frameworks)
• Excellent debugging and troubleshooting skills
• Clear communication and the ability to work independently within an agile team

Nice to haves

• Familiarity with CI/CD and DevOps workflows (Docker, Kubernetes, GitHub Actions)
• Experience deploying on Azure, Vercel, or Google Cloud
• Understanding of LLM evaluation and fine-tuning
• Basic Linux admin skills and comfort with monitoring tools like Prometheus
• Experience designing domain-specific conversational AI assistants

You are...

• Based in the UK
• Proactive and self-directed, with a strong sense of ownership
• Comfortable translating product requirements into clean, scalable code
• Thoughtful and collaborative when solving problems and reviewing architecture
• Motivated by building fast, reliable systems that support real-world users
• Excited to work with cutting-edge AI tools in a high-trust, async-first team

What we offer

• Remote work from anywhere in the UK
• Travel reimbursement for in-person meetups
• A personal learning and development budget to support your growth
• Flexible time-off policy with a culture of trust and balance
• Paid software subscriptions, from Cursor and ChatGPT to anything else you need to do your best work
• Discretionary bonuses when you go above and beyond

After you apply, we will

• Schedule an informal chat to see if we're a good fit
• Invite you to complete a short, take-home coding test
• Review the code together in a final technical interview
• Make you a job offer