Coderio designs and delivers scalable digital solutions for global companies. We combine strong technical expertise with a product mindset to lead complex software initiatives end-to-end. We work with international clients, value autonomy and clear communication, and build long-term partnerships through technical excellence.
🌍 More information: http://coderio.com
We are seeking an autonomous Senior Backend AI Engineer with 5+ years of software engineering experience and 2+ years dedicated to applied AI/LLM production systems. You should be a strong Python backend engineer who takes end-to-end ownership of systems, proactively solves complex engineering problems, and operates with a high degree of independence. You will join an agile project pod working alongside a Product Owner and Senior Engineers to build high-performance backend infrastructure that powers live AI products.
What You Can Expect (Responsibilities)
Refactor, maintain, and scale the core backend and AI framework layers of the platform, eliminating technical debt to support multi-tenant growth.
Implement and monitor production LLM observability, focusing on token cost optimization, retrieval strategy tuning, and real-time model/data drift detection.
Build and manage automated prompt versioning systems, A/B testing pipelines, and LLM evaluation frameworks to ensure high response quality and consistency.
Build out next-generation copilot services and agentic workflows that autonomously produce structured communications (emails, text messages, and call scripts).
Deliver reliable Python backend services, integrations, and APIs that interact directly with vector databases (Pinecone) and LLM providers.
Drive features from concept to production, working directly within client cloud environments while maintaining strong code quality and operational standards.
- 5+ years of overall software development experience with a heavy focus on backend systems.
- 3+ years of production-level engineering experience with Python.
- 2+ years of hands-on experience building, deploying, and maintaining Retrieval-Augmented Generation (RAG) systems in live production environments.
- 1+ years of hands-on experience integrating and utilizing LLM observability and tracing tools (e.g., LangFuse, LangSmith, or equivalent platforms).
- 1+ years of experience establishing prompt versioning, A/B testing, and evaluation frameworks for LLMs.
- 1+ years of experience implementing data drift and model drift monitoring for production AI workloads.
- Track record of operating as a true senior engineer—taking direct ownership of deliverables, resolving ambiguity, and driving technical execution without waiting for step-by-step instructions.
- Fluent English (spoken and written) for daily technical collaboration with US-based teams.
- 1+ years of experience developing agentic applications or copilot workflows (e.g., LangGraph, AutoGen, or custom agent frameworks) for automated content generation.
- 1+ years of hands-on experience with vector databases, specifically Pinecone.
- Experience with token cost management and retrieval optimization at scale.
- Background in the EdTech sector or working on plugin-based integrations.
100% remote work.
Long-term engagement with high impact and autonomy.
Strategic and high-visibility role within a modern engineering culture.
Opportunity to influence technical and business strategy.
Collaborative international team with strong technical leadership.
Clear growth path and leadership opportunities within Coderio.
At Coderio, we value talent and excellence. While we are primarily a remote-first company, this specific strategic role offers the opportunity to work directly on-site to drive high-stakes initiatives. We are passionate about technology, collaboration, and fair compensation. We offer an inclusive and challenging environment with real growth opportunities. If you are motivated to design solutions that make a difference, we are waiting for you. Apply now.
Skills Required
- 5+ years of overall software development experience with a heavy focus on backend systems
- 2+ years dedicated to applied AI/LLM production systems
- 3+ years of production-level engineering experience with Python
- 2+ years hands-on experience building, deploying, and maintaining RAG systems in production
- 1+ years integrating and utilizing LLM observability and tracing tools (e.g., LangFuse, LangSmith)
- 1+ years establishing prompt versioning, A/B testing, and evaluation frameworks for LLMs
- 1+ years implementing data drift and model drift monitoring for production AI workloads
- Track record of operating as a senior engineer taking ownership and driving technical execution independently
- Fluent English (spoken and written) for daily technical collaboration with US-based teams
- 1+ years experience developing agentic applications or copilot workflows (e.g., LangGraph, AutoGen)
- 1+ years hands-on experience with vector databases, specifically Pinecone
- Experience with token cost management and retrieval optimization at scale
- Background in EdTech or plugin-based integrations
What We Do
Accelerate your digital transformation with our expert nearshore engineering teams. From experienced Software Engineers to augment your tech team, to fully managed expert Development Squads. We design, engineer, and deliver customized technology solutions for companies of every size. We can assemble your enterprise-level dev squad within 7 days. Scale fast with our on-demand timezone-aligned software development talent. Contact us: [email protected]
