> Markdown version of [/jobs/ext/4294550-machine-learning-engineer-real-time-speech-translation](https://www.wearedevelopers.com/jobs/ext/4294550-machine-learning-engineer-real-time-speech-translation). Every page supports `.md` or `Accept: text/markdown`. Links point to the HTML versions so they work for humans too. Agent guide: [/agents.md](https://www.wearedevelopers.com/agents.md). --- # Machine Learning Engineer (Real-Time Speech Translation) - **Company:** Lilt Inc. - **Location:** Washington, DC, United States - **Experience:** Experienced - **Salary:** $120,000.0 - $161,434.0 - **Contract:** Permanent contract - **Skills:** Adobe Experience Manager, Application Programming Interfaces (APIs), Artificial Intelligence, Software Debugging, Multiplexing, Github, Python (Programming Language), Machine Learning, Machine Translation, Message Broker, Language Modeling, RabbitMQ, Prometheus, Salesforce.Com, Signal Processing, Data Streaming, Systems Integration, Speech Recognition, WebSocket, WebRTC, Datadog, Graphics Processing Unit (GPU), Load Balancing, Comet Programming, Google Drive, Large Language Models, Claude Code, AI Coding Agents, Backend, Agentic-AI, Kubernetes, Information Technology, Low Latency, Ray Serve, Machine Learning Operations, Front End Software Development, Webflow, Human in the Loop, Docker - **Published:** October 1, 2026 - **Apply:** https://www.indeed.com/viewjob?jk=c30b1cfc3eb94620 ## About the Role * 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) skills. * Hands-on experience with real-time streaming transport: WebSocket or gRPC bidirectional streaming, session state, backpressure, and connection lifecycle handling. * Experience serving ML models in production on GPUs (Ray Serve, Triton, vLLM, or similar), with Docker and Kubernetes. * Experience integrating speech or NLP models into production systems, ideally streaming ASR (partial hypotheses, endpointing, VAD). * A latency-engineering mindset: you have profiled, instrumented, and optimized a real-time or low-latency system and can reason in per-stage budgets. * Effective use of AI coding agents (Claude Code, Codex, or similar) on top of fundamentals learned the hard way: you let agents do the typing, but you can debug, review, and reason about every line without them, and you know when not to trust them. * US citizenship and residence in the United States (contract requirement)., * Ray Serve specifically, including streaming responses and model multiplexing. * Familiarity with simultaneous or incremental MT concepts (retranslation, prefix stability, wait-k policies). * Machine translation quality estimation (COMET/CometKiwi class models) or other confidence estimation in production. * Message brokers for real-time fan-out and state distribution (RabbitMQ or similar). * Streaming text-to-speech integration and time-to-first-audio optimization. * WebRTC and SFU concepts, or voice pipeline frameworks (LiveKit Agents, Pipecat). * Handling of CJK and other non-Latin text in NLP pipelines (our first languages are Japanese, Korean, and English). * Observability tooling (Datadog, Prometheus) for production ML systems. ## Description * Real-time pipeline architecture: Build and manage services for high-throughput, real-time audio and text streaming. Handle signal processing, session lifecycles, and concurrency management to ensure robust operation under load. * ML model integration: Integrate and serve streaming speech recognition and machine translation models, collaborating with research teams to ensure models operate within required latency budgets. * Quality and confidence workflows: Develop logic for model-based confidence scoring, routing segments for human intervention as needed, and broadcasting real-time updates and corrections to end-users. * Infrastructure and scale: Architect and scale production ML infrastructure on GPU-accelerated Kubernetes clusters. Implement batching, load balancing, and autoscaling strategies to maintain performance and cost-efficiency. * Latency engineering: Establish comprehensive instrumentation for real-time performance. Identify bottlenecks, optimize system throughput, and drive down end-to-end latency metrics to meet production standards. * Interface and API definition: Define technical contracts and interfaces for audio ingestion and downstream service integrations. Partner with frontend and platform engineering teams to maintain clean, robust integration points. * Collaboration and technical leadership: Drive cross-team alignment by defining clear API interfaces and technical contracts, facilitating effective communication between engineering and product teams to ensure seamless system integration., * Brand-aware AI that learns your voice, tone, and terminology to ensure every translation is accurate and consistent * Agentic AI workflows that automate the entire translation process from content ingestion to quality review to publishing * 100+ native integrations with systems like Adobe Experience Manager, Webflow, Salesforce, GitHub, and Google Drive to simplify content translation * Human-in-the-loop reviews via our global network of professional linguists, for high-impact content that requires expert review LILT in the News * Featured in The Software Report's Top 100 Software Companies! * LILT makes it onto the Inc. 5000 List. * LILT's continues to be an intellectual powerhouse, holding numerous patents that help power the most efficient and sophisticated AI and language models in the industry. * Check out all our news on our website. Information collected and processed as part of your application process, including any job applications you choose to submit, is subject to LILT's Privacy Policy at https://lilt.com/legal/privacy. At LILT, we are committed to a fair, inclusive, and transparent hiring process. As part of our recruitment efforts, we may use artificial intelligence (AI) and automated tools to assist in the evaluation of applications, including résumé screening, assessment scoring, and interview analysis. These tools are designed to support human decision-making and help us identify qualified candidates efficiently and objectively. All final hiring decisions are made by people. If you have any concerns, require accommodations, or would like to opt-out of the use of AI in our hiring process, please let us know at recruiting@lilt.com.