Senior AI Engineer

About the role

Propio Language Services is a top-five global language services provider and the fastest-growing company in the industry. Operating at nine-figure scale across healthcare, legal, and other sectors, Propio delivers high-quality, real-time multilingual interpretation, translation, and localization services. Driven by cutting-edge technology and exceptional service, we create seamless experiences that bridge communication gaps across languages, cultures, and communication channels.

Responsibilities

• Own the architecture, development, and delivery of enterprise-grade AI systems from concept to production, including LLM, generative AI, agentic, multimodal, speech AI, and machine learning systems.
• Prototype, build, and deploy real-time AI applications and infrastructure for speech, voice agents, LLM-powered workflows, and other latency-sensitive AI experiences.
• Lead the development of AI capabilities including agent orchestration, tool calling, RAG, structured generation, memory, reasoning workflows, guardrails, and evaluation systems.
• Evaluate and select models, architectures, frameworks, and technologies based on measurable tradeoffs across quality, latency, reliability, scalability, and cost.
• Stay current with emerging AI research and industry trends, rapidly prototype new AI approaches and convert successful experiments into reliable, scalable, and maintainable production systems.
• Mentor engineers, conduct high-quality design and code reviews, and influence technical direction across a team.

Qualifications

• Master's degree in Engineering, preferably in Computer Science, Statistics, Data Science, or a related field, or equivalent relevant work experience.
• 7+ years of hands-on full-stack software engineering experience, with significant experience building production-grade AI/ML backend systems and strong proficiency in Python.
• 3+ years of experience building production-grade modern AI systems, particularly real-time speech AI, speech-to-text, text-to-speech, voice agents, conversational AI, multimodal systems, or agentic systems.
• Experience building and operating production systems on cloud platforms in AWS, including production-grade CI/CD and infrastructure-as-code tools such as AWS CDK.
• Experience with real-time speech AI systems, real-time audio processing, or other latency-sensitive applications, using technologies or platforms such as OpenAI, Deepgram, Whisper, Hugging Face Transformers, or similar tools.
• Experience building multi-agent or complex agent orchestration systems using LangChain or similar frameworks.
• Experience working in healthcare, legal, or other regulated environments, including familiarity with AI safety, HIPAA, PHI, and Section 1557 requirements.
• Prior experience with multilingual AI systems or low-resource language challenges is a plus.

This may not be the right role for you if:

• You prefer primarily coordinating projects rather than designing and building systems yourself.
• Your AI experience is primarily limited to integrating third-party AI APIs without owning the underlying architecture, evaluation, reliability, or production behavior.
• You rely primarily on prompt experimentation without systematic evaluation, metrics, testing, or engineering rigor.
• You have primarily built demos or prototypes and have limited experience operating AI systems in production.
• You prefer working from detailed specifications rather than owning ambiguous technical problems from problem definition through implementation.
• You are looking for a people-management-only role.
• You are uncomfortable diving into code, debugging production issues, or reviewing critical technical implementations.
• You are uncomfortable making technical decisions when information is incomplete and there is no obvious solution.