AI/ML Engineer — LLM & Application Development
Bivoxo is hiring an AI/ML Engineer. Design and build intelligent applications using large language models, custom AI pipelines, and ML frameworks that deliver measurable, real-world business outcomes for our clients.
Responsibilities:
- Design and build production AI features for real client products — RAG pipelines, LLM-powered workflows, and custom AI integrations, not research demos.
- Work directly with the OpenAI API (and comparable LLM providers) to build features that solve genuine business problems, not tech-for-tech's-sake gimmicks.
- Architect and optimize retrieval pipelines — embeddings, vector search, prompt design — for accuracy, latency, and cost.
- Partner with full-stack engineers to ship AI features inside real Next.js/Node applications, end-to-end.
- Evaluate model performance rigorously, and know when a fine-tuned model, better prompting, or better retrieval will actually move the needle.
- Keep a close eye on cost and latency — production AI features have to work at real usage volume, not just in a demo.
- Stay ahead of the model/tooling landscape and bring back what's actually useful, filtering out the hype.
Build AI Features That Ship, Not Just Demo
You'll work close to the metal of the stack — OpenAI's API, vector search, prompt and retrieval design — while staying grounded in what actually matters to the client: is this feature fast, accurate, cost-effective, and does it solve a real problem. Hype-driven AI work doesn't survive here; shipped, working AI does.
Requirements:
- 3+ years building production applications with LLMs — RAG pipelines, prompt engineering, embeddings/vector search, or fine-tuning.
- Strong Python (or Node.js) skills and hands-on experience with the OpenAI API or comparable LLM providers.
- Solid understanding of vector databases (pgvector, Pinecone, or similar) and retrieval architecture trade-offs.
- Comfortable partnering with full-stack engineers to ship AI features inside real applications — not handing off a notebook and walking away.
- A pragmatic mindset: you optimize for what actually improves the product, not what's trendiest on X.
- Clear communicator who can explain AI trade-offs (cost, latency, accuracy) to non-technical stakeholders.
- Bonus: experience with fine-tuning, evaluation frameworks, or MLOps for LLM-based systems.
Got Questions? We've Got Answers.
We believe in clarity and transparency. Find quick answers to the most common questions about automation, our process, and how we can help your business.
Businesses of all sizes and across various industries can benefit, especially those with repetitive, high-volume tasks, data processing needs, or a desire to improve efficiency and reduce operational costs.
Project timelines vary depending on complexity, scope, and the specific technologies involved. We'll provide a detailed timeline after our initial assessment.
While ROI varies, clients often see significant returns through reduced operational costs, increased efficiency, improved accuracy, and enhanced employee productivity. Our audit can provide a personalized estimate.
Not at all! Our team handles the technical implementation, integration, and ongoing support. Your role is to define your business needs, and we'll translate them into automated solutions.
Data security and compliance are paramount. We implement robust security protocols, adhere to industry best practices, and ensure solutions meet relevant regulatory requirements specific to your industry.
Ready to Elevate Your Business with Intelligent Automation?
Partner with the experts at Bivoxo to unlock new levels of efficiency, drive innovation, and secure a competitive advantage. Let's discuss your unique needs.
_compressed.webp)
_compressed.webp)
_compressed.webp)
_compressed.webp)