### Full Job Description
We are looking for a talented **AI Engineer** to design, build, and maintain
AI-powered consumer applications that help people understand, learn,
communicate, and work more effectively. In this role, you will develop
practical software products that solve real-world problems through artificial
intelligence, automation, and intuitive user experiences.
Our first product, **CAPCUE** , demonstrates our vision of creating software
that enhances human productivity and accessibility through AI. CAPCUE is a
Windows desktop application that provides real-time AI-powered captions for
any audio played on a computer, including meetings, lectures, livestreams,
videos, podcasts, and other media sources.
As the company grows, we plan to develop additional consumer-focused software
products across productivity, education, communication, accessibility, and
other technology-driven categories. This role is ideal for an engineer who can
combine strong software engineering skills with modern AI, LLM, and cloud-
native development practices.
### Responsibilities
* Design, develop, and maintain **AI-powered consumer applications** using modern engineering practices and scalable architectures.
* Build and integrate **LLM-based features** using models such as GPT, Claude, Gemini, and open-source LLMs.
* Develop and optimize **RAG systems** , including document ingestion, embeddings, vector search, retrieval pipelines, prompt engineering, and response generation.
* Build AI workflows involving **speech-to-text, real-time transcription, natural language processing, summarization, classification, and automation**.
* Design scalable backend services using **Python, TypeScript, Node.js, PostgreSQL, Redis, Docker, and cloud services**.
* Develop reliable APIs and services that support real-time AI functionality with low latency and high availability.
* Work with vector databases and search technologies such as **Pinecone, Weaviate, Chroma, FAISS, pgvector, Elasticsearch, or similar tools**.
* Improve AI system quality through prompt evaluation, automated testing, model monitoring, feedback loops, and performance optimization.
* Build observability into AI systems using logging, metrics, tracing, error tracking, and production monitoring tools.
* Collaborate with product, design, and engineering teams to translate product requirements into reliable AI-powered features.
* Participate in code reviews, architecture discussions, and technical planning to ensure code quality, scalability, security, and maintainability.
* Take ownership of features from design and development through deployment, monitoring, and continuous improvement.
* Contribute to the evolution of the company’s AI architecture, infrastructure, and development standards.
### What You’ll Bring
* 4+ years of professional software engineering experience, with strong experience building production applications or backend services.
* Hands-on experience building AI-powered applications using **LLMs, RAG, embeddings, vector databases, prompt engineering, and AI APIs**.
* Strong programming skills in **Python** and/or **TypeScript/Node.js**.
* Experience working with LLM providers and frameworks such as **OpenAI, Anthropic, Google Gemini, LangChain, LlamaIndex, Hugging Face, or similar tools**.
* Strong understanding of AI application development, including prompt design, retrieval quality, model evaluation, latency optimization, and cost management.
* Experience with databases such as **PostgreSQL, Redis, and vector search systems**.
* Experience designing and consuming REST APIs, streaming APIs, and event-driven services.
* Familiarity with **speech recognition, audio processing, transcription systems, or real-time AI pipelines** is a strong plus.
* Experience with Docker and cloud platforms such as **GCP, AWS, or Azure**.
* Understanding of software engineering best practices, including clean code, testing, code reviews, CI/CD, version control, and production operations.
* Ability to debug complex systems, improve performance, and build reliable software for real users.
* Strong communication skills and the ability to work effectively in a collaborative product-focused environment.
* Experience with Agile software development practices.
### Preferred Qualifications
* Experience building real-time AI applications, transcription tools, captioning systems, accessibility tools, or productivity software.
* Experience with **Whisper, Deepgram, AssemblyAI, Google Speech-to-Text, Azure Speech, or other speech-to-text technologies**.
* Experience deploying AI systems in production with monitoring, evaluation, and feedback collection.
* Familiarity with **Kubernetes, serverless platforms, hybrid cloud infrastructure, or distributed systems**.
* Experience optimizing AI systems for latency, accuracy, scalability, and cost efficiency.
* Experience working with open-source LLMs, model hosting, inference APIs, or fine-tuning workflows.
* Experience building consumer-facing desktop, web, or cross-platform applications.
* Strong interest in building AI products that improve accessibility, learning, communication, and productivity.
### About the Role
This is a hands-on engineering role focused on building real AI products used
by consumers. You will work across backend engineering, AI system design, LLM
integration, RAG pipelines, real-time processing, and production deployment.
The ideal candidate is not only comfortable using AI tools and APIs, but also
understands how to build reliable, scalable, and user-friendly AI-powered
software.
We are looking for someone who enjoys solving practical problems, shipping
product features, and improving AI systems based on real user needs.