Senior AI Engineer
Build and scale low-latency speech and LLM systems powering conversational healthcare voice agents. The role requires 3–5 years of end-to-end product engineering experience, distributed-systems expertise, and familiarity with the modern Python and React stack.
About the job
Responsibilities
- Design and scale Prosper’s real-time AI platform.
- Build low-latency speech and LLM pipelines, orchestration layers, and reliability systems.
- Engineer systems that sound human, reason under strict latency constraints, and adapt to complex healthcare conversations.
- Deploy AI voice agents handling thousands of daily phone calls.
- Build products end to end, from solution architecture through production deployment.
- Manage large-scale distributed systems with asynchronous workload orchestration.
Requirements
- 3–5 years of experience building products end to end, from architecting solutions to deploying production-grade software.
- Strong understanding of FastAPI, Python, PostgreSQL, React, and TypeScript, or equivalent technologies in other languages.
- Experience managing large-scale distributed systems with asynchronous workload orchestration.
- Bachelor’s or master’s degree in Computer Science, Engineering, Mathematics, Physics, or a related field, or equivalent experience.
- Ownership mindset and willingness to work hard in a fast-growing environment.
Nice to Have
- Familiarity with large language models, AI agents, or other machine-learning models.
- Experience with Pipecat for voice agents.
Compensation and Benefits
- Full-time role based in the Barcelona office, with the possibility of moving to the New York office.
Skills
FastAPI, Python, Postgres, React, TypeScript, Distributed Systems, Asynchronous Workload Orchestration, LLMs, AI Agents, Machine Learning, Pipecat, Voice Agents
Similar jobs
ML Engineering jobs
Datadog
Bordeaux, FranceBuild and operate AI-powered, customer-facing workflows for Datadog Notebooks, combining reliable backend systems with LLM capabilities. The role requires 6+ years of engineering experience, Go or Python expertise, and experience delivering production AI products.
Hudl
Barcelona, SpainBuild and operate edge MLOps infrastructure for smart-camera machine-learning systems, including model deployment, TensorRT compilation, fleet updates, telemetry, and reliability. The role requires production MLOps experience, embedded inference optimization, and strong collaboration with data-science and embedded-engineering teams.
Payabli
Remote
Sets the technical direction for production machine learning across a payments platform, building and scaling models for risk, authorization, disputes, and forecasting. Requires 8+ years of ML engineering experience, including production model ownership and strong technical leadership.
Protege
Remote
Build the technical foundation for a new business vertical, creating reusable infrastructure and leading early customer engagements from scoping through delivery. The role requires 3+ years of engineering experience, strong Python and SQL skills, backend/data expertise, and comfort operating in ambiguity.
Twilio
United StatesBuild and deploy AI-powered features for conversation intelligence, developing production ML pipelines and inference services for voice and messaging data. The role requires 2+ years of applied ML experience, Python, an ML framework, NLP familiarity, and cloud infrastructure experience.