Real-Time Speech Translation ML Engineer

LILT AI; Indianapolis (IN); On-site; USD 120,000 - 160,000; Full time

Job summary

LILT AI in the United States is building a new live translation backend. We are seeking an ML Engineer to own the real-time speech translation backend end-to-end, from live audio input to translated output.

You will integrate ASR and MT models on Ray Serve with Kubernetes, optimize for low latency, and work closely with researchers and architects. The role requires deep Python expertise, async programming, and production ML infrastructure experience.

Qualifications

• BS or MS in Computer Science or a related field, or equivalent practical experience.
• 3+ years building production backend or ML serving systems in Python, including strong async programming (asyncio).
• Hands-on experience with real-time streaming transport: WebSocket or gRPC bidirectional streaming, session state, backpressure, and ...

Responsibilities

• Real-time pipeline architecture: Build and manage services for high-throughput, real-time audio and text streaming.
• ML model integration: Integrate and serve streaming speech recognition and machine translation models, collaborating with research teams.
• Quality and confidence workflows: Develop logic for model-based confidence scoring, routing segments for human intervention as needed.
• Infrastructure and scale: Architect and scale production ML infrastructure on GPU-accelerated Kubernetes clusters.
• Latency engineering: Establish instrumentation for real-time performance and optimize end-to-end latency.
• Interface and API definition: Define technical contracts and interfaces for audio ingestion and downstream services.
• Collaboration and technical leadership: Drive cross-team alignment with clear API interfaces and contracts.

Skills

Python

Asyncio

Backend engineering

ML serving

Education

BS/MS in CS

Equivalent practical experience

Tools

WebSocket

gRPC

Job description

LILT AI in the United States is building a new live translation backend. We are seeking an ML Engineer to own the real-time speech translation backend end-to-end, from live audio input to translated output.

You will integrate ASR and MT models on Ray Serve with Kubernetes, optimize for low latency, and work closely with researchers and architects. The role requires deep Python expertise, async programming, and production ML infrastructure experience.