Software Engineer
Software Engineer at Beaverhand — US
- Company: Beaverhand
- Location: US
- Posted: 2025-11-10
About this role
Location: Hybrid (Portland, OR or Remote – US-Based)
About the Role
We’re looking for a Mid-Level Software Engineer with hands-on experience in Generative AI to help build intelligent, scalable, and user-centric AI applications. You’ll work closely with our product, data, and AI teams to design and implement real-world solutions powered by large language models (LLMs), vector databases, and custom agentic systems.
This role is perfect for an engineer who’s comfortable writing production-level code and experimenting with cutting-edge AI frameworks. You’ll own features end-to-end—from architecture and data ingestion to evaluation and deployment—while collaborating with a small, high-impact team that values creativity, autonomy, and pragmatic execution.
What You’ll Do
Design, build, and maintain production-ready software that integrates with LLMs (OpenAI, Anthropic, etc.) and other AI APIs.
Implement RAG (Retrieval-Augmented Generation) pipelines using tools like Qdrant, Pinecone, or FAISS.
Work with prompt engineering, fine-tuning, and evaluation techniques to improve LLM output accuracy and alignment.
Build internal tools and APIs to support AI-driven workflows and user-facing features.
Collaborate with product managers, designers, and AI researchers to translate product requirements into scalable architectures.
Contribute to prompt libraries, evaluation frameworks, and model orchestration (LangChain, LlamaIndex, DSPy, etc.).
Write clean, maintainable, and well-tested code.
Stay current on emerging trends in GenAI and propose creative ways to leverage them in production systems.
What You Bring
3–6 years of software engineering experience (Python, TypeScript, or Go preferred).
At least 1 year of hands-on experience building with Generative AI tools, including OpenAI, Anthropic, or open-source LLMs.
Solid understanding of API design, distributed systems, and database fundamentals.
Experience with vector databases and embedding pipelines.
Familiarity with LangChain, LlamaIndex, Hugging Face, or similar frameworks.
Comfortable working in cloud environments (AWS, GCP, or Azure) and using containerization (Docker, Kubernetes).
Strong problem-solving and communication skills; you thrive in collaborative, iterative environments.
Passion for the intersection of AI, creativity, and human-centered product design.
Bonus Points
Experience deploying multi-agent systems or autonomous AI tools.
Familiarity with frontend frameworks (React, Next.js) for integrating AI features.
Background in MLOps, data engineering, or prompt evaluation metrics.
Contributions to open-source AI projects.