Sr. Generative AI Engineer

Description:

About BELVA

At Belva, we’re not just building technology — we’re redefining how people interact with it.

We believe tech should serve a higher purpose: making life better. Our mission is to liberate people from repetitive work so they can focus on what truly matters. With ethical, privacy-first AI at our core, we empower individuals and organizations to work smarter and reclaim their time.

Belva is a trailblazing AI company fueled by curiosity, grit, and an unwavering commitment to progress. We value passion, attitude, and potential over pedigrees — because while skills can be learned, vision and leadership come from within. If you’re ready to help shape the future of AI and build tools that truly serve people, we’d love to hear from you.

Position Overview

We are looking for a hands-on and highly capable Sr. Gen AI Engineer to join our growing AI team. As an early team member at a fast-paced and ambitious AI start-up, you’ll play a key role in building production-grade AI applications that integrate cutting-edge GenAI capabilities.

Requirements:

As a Sr. Gen AI Engineer, you will collaborate with other engineers to build, evaluate, and iterate on AI-powered systems. You’ll bring a deep understanding of GenAI technologies and strong software engineering skills to bear on solving real-world problems through well-architected, testable, and observable solutions.

NOTE: Must be a Citizen or Green Card Holder and live in the United States.

Required Experience:

• B.S. degree in Computer Science (or equivalent field) or 10+ years of experience in the software development / AI field
• 7+ years of overall software development experience
• 2+ years of hands-on experience working closely with Generative AI systems
• Understanding of strengths and weaknesses of various foundational models
• Advanced proficiency in Python, especially with AI/ML libraries and tooling
• Expertise in prompt engineering, including structured prompt design and optimization
• Experience creating agentic workflows and using orchestration frameworks (e.g., LangChain, LangGraph)
• Exposure to human-in-the-loop (HITL) workflows and agent UX considerations
• Experience building chat-based UX features
• Solid understanding of best practices in context engineering
• Demonstrated ability to evaluate and monitor LLM models in production, including A/B testing and observability practices
• Experience generating and using synthetic datasets for evaluation or testing
• Startup experience—comfortable wearing multiple hats and working with ambiguity
• Outstanding communication skills—clear, concise, and effective in both writing and speech

Nice to haves:

• Experience integrating agents via Model Context Protocol (MCP)
• Experience with fine-tuning open-source LLMs and managing LLM Ops workflows
• Familiarity with AWS, voice APIs, or multi-modal LLMs