Build the production infrastructure for Rezo.ai's speech platform, owning audio pipelines, real-time inference services, and ML training infrastructure.

About the Company

Rezo.ai is an innovative technology company specializing in conversational AI and voice platforms. We build intelligent systems that process and understand human speech at scale, serving enterprise clients who need reliable, low-latency voice interactions. Our team combines deep expertise in machine learning, backend engineering, and telephony infrastructure to deliver production-grade speech solutions.

Role Overview

We are looking for a Senior Backend Engineer to join our speech platform team. In this role, you will be the engineering owner on the speech team, working alongside two ML engineers. Your primary focus will be building everything around the models — ingestion, training infrastructure, real-time serving, and integration into our existing platform. This is a pure backend engineering role. You do not need to train models; you need to build the systems that make trained models useful in production.

Key Responsibilities

• Build the audio data pipeline: mine our call archive, transcode, resample, segment, deduplicate and quality-filter at scale
• Build and operate real-time inference services with hard latency targets, including streaming, cancellation and mid-utterance interruption
• Integrate speech services into our existing Java-based platform and telephony infrastructure
• Instrument the full latency budget end-to-end and find where the milliseconds go
• Stand up training infrastructure — GPU scheduling, checkpointing, experiment tracking, reproducibility
• Own compute cost and concurrency economics: how many simultaneous calls per GPU, and how to improve it
• Support on-premise deployment for clients who can't send data outside their network

Tech Stack

• Languages: Java (primary), Python
• Streaming/Real-time: WebSocket, gRPC streaming
• Data Pipelines: Airflow, Dagster, Spark
• Containerization/Orchestration: Docker, Kubernetes
• Cloud: AWS, GCP, or Azure
• ML Serving (nice to have): Triton Inference Server, vLLM, TorchServe
• Audio Tools (nice to have): ffmpeg, sox
• Telephony (nice to have): SIP, Asterisk/FreeSWITCH
• MLOps (nice to have): MLflow, Weights & Biases, DVC
• GPU Infrastructure (nice to have): GPU scheduling, checkpointing

If you are passionate about building robust, low-latency systems that power real-time speech AI, this role offers an exciting opportunity to make a significant impact.

• 3–4 years building and operating production backend systems
• Strong Java — you've owned services in production, not just contributed to them
• Working Python — enough to build data pipelines and integrate with ML tooling
• Real-time or low-latency systems experience: streaming APIs, WebSocket or gRPC streaming, concurrency, backpressure
• Data pipelines at scale (Airflow, Dagster, Spark or equivalent)
• Docker and Kubernetes in production
• Cloud infrastructure (AWS/GCP/Azure)
• Comfortable debugging performance: profiling, latency percentiles, throughput under load
• Nice to have: Serving ML models in production (Triton, vLLM, TorchServe)
• Nice to have: Audio tooling — ffmpeg, sox, codecs, resampling
• Nice to have: Telephony — SIP, Asterisk/FreeSWITCH, media servers, narrowband codecs
• Nice to have: MLOps tooling: MLflow, Weights & Biases, DVC
• Nice to have: GPU-aware infrastructure work

• Competitive salary and equity
• Opportunity to work on cutting-edge speech AI technology
• Collaborative team with ML engineers and platform experts
• Flexible working hours
• Health insurance coverage
• Professional development budget