Senior Full Stack Engineer

Lilt's Converse product delivers real-time, multi-party translation for high-stakes conversations - from offline, device-based deployments in the field to live meetings on enterprise collaboration platforms. Were expanding Converse to support any number of participants, speaking any combination of languages, joining from a growing set of form factors - with live translation delivered N-way, directly on the meeting stage, and cleared interpreters reviewing only the segments that need a human eye. Every deployment has a different topology - device count, platform, network conditions, and language mix - and making a single translation architecture work reliably across that diversity is a real engineering challenge. You will help own this expansion end-to-end: architecture, product roadmap, and the hands-on engineering that gets a brand-new real-time product surface to GA. This is a high-impact, ground-floor role on a new product line within a company whose existing products serve some of the worlds largest global brands.

As the senior engineer on the Create team driving this Converse expansion, you will drive technical strategy for both the backend translation service and the customer-facing surfaces built on top of it, while working directly with Product, Design, and early design partners - architecting the low-latency streaming pipeline, building the live meeting experience and interpreter workbench, and turning ambiguous 0-to-1 requirements into a scoped plan you commit to and ship. You will partner with the engineers already building Converses device/mobile experience to extend a shared translation-service architecture into new platforms and form factors, help define engineering standards as the Create team grows, and make the calls that determine whether this expansion scales cleanly from a prototype into a production product used in live, multilingual meetings.

Location & eligibility: This position requires US citizenship and residence in the United States. Preferred locations are Washington, D.C.; Boston, MA; and Indianapolis, IN.
What Youll Do

• Own architecture and technical roadmap for this Converse expansion, spanning the central real-time translation service and the customer-facing surfaces built on it (live meeting UI, interpreter workbench)
• Architect and build the low-latency, N-way translation pipeline: per-participant audio ingestion, diarization, streaming ASR, MT orchestration, and result fan-out to every language in the meeting
• Build the live meeting experience - bot/agent participant, meeting side panel, and on-stage caption surfaces - integrating with the host meeting platforms SDK, extension framework, and APIs
• Build the interpreter workbench: a real-time, streaming adaptation of Lilts CAT tool with a live segment queue, low-confidence flagging, TM/TB matches, AI-Review/AI-QA signals, and submit-to-broadcast corrections
• Design the event-driven correction and broadcast system - routing flagged segments to the correct on-call interpreter by language, pausing the affected translation, and isolating each correction to a single language
• Partner with Product and Design to turn PRD requirements (JTBD, feature specs) into technical designs, and commit to and hit delivery dates on a brand-new product surface
• Collaborate with the engineers already building Converses device/mobile experience to extend a shared translation-service architecture (per-participant declared spoken/received languages) into new multi-device and platform form factors
• Establish testing, CI/CD, and release practices (GitHub Actions, automated e2e tests) for the new product line
• Help recruit, mentor, and set engineering standards as headcount scales on this initiative

What Were Looking For
Required

• 5+ years of professional full-stack software engineering experience, with a track record of owning complex, real-time or streaming systems end-to-end - architecture, implementation, deployment, and production reliability
• Strong backend experience spanning REST API endpoints and real-time/streaming systems: WebSockets, gRPC, or comparable low-latency transport; event-driven architectures; message routing and state management across many concurrent sessions
• Strong frontend experience building complex, stateful, real-time UIs in React/TypeScript - live-updating multi-pane interfaces, collaborative editors, or comparable dashboards
• Experience integrating with third-party platform SDKs or extension frameworks (Slack, Zoom, or similar meeting/collaboration platforms) - bots, side panels, webhooks, and platform APIs
• Comfort working with or directly adjacent to ASR/MT/NLP pipelines, or other latency-sensitive ML-in-the-loop systems
• Demonstrated ability to scope ambiguous, 0-to-1 product requirements into a technical plan and commit to and hit delivery dates
• Experience building validation and guard logic that gracefully handles edge cases across diverse customer configurations - languages, device counts, network conditions
• US citizenship and residence in the United States

Strong Plus

• Experience with speech/audio pipelines: diarization, streaming speech recognition, or audio stream multiplexing
• Prior experience building CAT tools, translation memory/termbase systems, or other linguist-facing review interfaces
• Familiarity with localization/TMS workflows: XLIFF, Translation Memory, MT vs. human translation pipelines
• Experience with cross-platform, embedded, or mobile-adjacent architectures, and adapting shared services across device and web form factors
• Experience shipping in regulated or high-security customer environments

Bonus

• Hands-on Microsoft Teams app or bot development specifically (Teams Toolkit, Bot Framework, Azure Communication Services, Microsoft Graph)
• Experience mentoring engineers and setting technical standards for a new product line
• Familiarity with post-meeting asset generation: transcript export formats (TXT/WebVTT/JSON), recording citations, and summarization