Real-Time Speech Translation Backend Engineer

Lilt; United States; On-site; USD 140,000 - 190,000; Full time

Benefits offered by this job

Medical benefits

401(k) matching

Equity

Job summary

Lilt is hiring an ML Engineer to own the real-time speech translation backend end-to-end. You will connect live audio input to translated output, building on Ray Serve on GPU Kubernetes clusters and in-house MT models.

You’ll work with architects and researchers to achieve low latency and reliable production service. The role requires Python expertise, real-time streaming experience, and the ability to optimize ML stack from models to infrastructure, with a strong emphasis on cost‑aware hardware

Qualifications

• 3+ years building production backend or ML serving systems in Python
• Experience integrating speech or NLP models into production systems, ideally streaming ASR
• US citizenship and residence in the United States (contract requirement)
• Hands‑on experience with real‑time streaming transport: WebSocket or gRPC bidirectional streaming
• A latency‑engineering mindset: you have profiled, instrumented, and optimized a real‑time or low‑latency system
• Experience serving ML models in production on GPUs (Ray Serve, Triton, vLLM) with Docker and Kubernetes
• Effective use of AI coding agents on top of fundamentals learned the hard way
• Observability tooling (Datadog, Prometheus) for production ML systems
• Handling of CJK and other non-Latin text in NLP pipelines
• Streaming text-to-speech integration and time-to-first-audio optimization
• Machine translation quality estimation or confidence estimation in production
• Familiarity with streaming data architectures and message brokers

Responsibilities

• Build the real-time speech translation backend end-to-end, from live audio input to translated output
• Integrate and serve streaming ASR and MT models within latency budgets
• Architect and scale production ML infrastructure on GPU‑accelerated Kubernetes clusters
• Implement batching, load balancing, and autoscaling for performance and cost‑efficiency
• Define API contracts for audio ingestion and downstream services
• Collaborate with product and research teams to meet latency targets
• Drive cross‑team alignment and code reviews using AI agents responsibly

Skills

Python proficiency

Async programming

Latency engineering

Production backend

Real-time streaming

Observability tooling

AI coding agents

Education

Bachelor's or Master’s in CS or related

Tools

WebSocket

gRPC

Docker

Kubernetes

Ray Serve

Triton

vLLM

LiveKit

RabbitMQ

Job description

Lilt is hiring an ML Engineer to own the real-time speech translation backend end-to-end. You will connect live audio input to translated output, building on Ray Serve on GPU Kubernetes clusters and in-house MT models.

You’ll work with architects and researchers to achieve low latency and reliable production service. The role requires Python expertise, real-time streaming experience, and the ability to optimize ML stack from models to infrastructure, with a strong emphasis on cost‑aware hardware