AI Architect – Voice AI

🔥 0 minutes ago

🇵🇱 Poland – Remote

⏳ Contract/Temporary

🟡 Mid-level

🟠 Senior

🤖 AI Engineer

👻 Ghost score 19%

What it means: how likely this posting is sitting open without active hiring.How to read it: 60% or higher means we think this is a ghost. Lower scores are less of a worry.How we score it: age, reposts, open roles vs team size, how fast jobs close, and whether pay is listed.Fine print: an estimate from public data, not a judgment of the company. Real jobs can score high, so treat it as a hint, not a fact.

Apply Now

Find Similar Remote Jobs

Set Up Email Alert For New Jobs

📊 Check your resume score for this job

Improve your chances of getting an interview by checking your resume score before you apply.

Upload Resume

Neurons Lab

WebsiteLinkedInAll Job Openings

51 - 200 employees

🤖 Artificial Intelligence

🏥 Healthcare

⚡ Energy

💰 Corporate Round on 2022-10

Artificial Intelligence • Healthcare • Energy

Neurons Lab is a globally distributed AI R&D company that helps deep tech innovators to accelerate data-driven products development and launch. Our team has expertise in fundamental sciences, full-stack AI/ML engineering, and product design. Such a rare combination and access to scarce talent allows Neurons Lab to build disruptive solutions for clients in HealthTech and EnergyTech industries.

📋 Description

• Own the technical architecture and delivery of the voice copilot from validated PoC to production • Meet latency, accuracy, concurrency, and cost targets • Keep production-polish expectations aligned and prevent silent scope creep • Transfer knowledge continuously to the client team and Neurons Lab engineers • Own the full pipeline: streaming speech-to-text, LLM field extraction, Chrome-extension delivery, and AWS infrastructure • Reduce P95 latency from approximately 6 seconds toward 2 seconds and resolve post-processing lag corner cases • Run Claude Haiku versus GPT Luna model A/B tests using golden-set evaluation for phonetic name and email accuracy • Own Langfuse traces, accuracy dashboards, live-call per-call cost measurement, and optimization planning • Harden the system for 5–10+ concurrent calls with strict user data isolation, monitoring, alerting, and safe rollback • Deliver epics end to end, including the Amazon SES email briefing service, while maintaining a demo fallback • Lead technical discussions with the client and present measurable system behavior • Tie feedback to the SOW and route roadmap items to future phases • Ensure client-facing materials pass ADM review • Lead the AI Engineer and pod by assigning tasks, reviewing output, and removing blockers • Absorb the outgoing architect's handover and become independent quickly • Run knowledge-transfer sessions to eliminate single points of failure • Provide estimates and architecture options for the production SOW when requested

🎯 Requirements

• Hands-on experience with real-time voice pipelines: streaming STT, turn handling, and low-latency LLM inference • LLM engineering experience: prompt engineering, structured extraction, guardrails, and model A/B evaluation • Experience with observability and evaluations, including Langfuse or similar, golden datasets, and latency, accuracy, and cost dashboards • AWS experience with Bedrock, serverless patterns, SES, token economics, and per-call cost engineering • Strong Python skills • Sufficient TypeScript and Chrome-extension knowledge to own the integration • Clear spoken and written English for demanding US executives • Knowledge of contact-center and agent-assist patterns and metrics, including handle time, cost per call, and concurrency • Production LLM operations experience, including load testing, data isolation, and incident handling • Voice AI in production is mandatory; must have shipped at least one real-time voice or speech product to real users • 6+ years of hands-on AI/ML engineering experience with strong recent LLM production practice • Demonstrated latency and reliability record, including measured P95 reductions and concurrency fixes on a live system • Consulting/client-facing seniority and ability to manage detailed UAT scrutiny and expectations • Nice to have: empathy-sensitive domain experience in healthcare, veterinary, or insurance; PE-sponsored rollouts; Chrome extension delivery; telephony/streaming stacks such as Amazon Connect, Twilio, or LiveKit; Langfuse in production; US client experience with Eastern-time overlap • Required English level: Intermediate, Upper Intermediate, or Advanced options listed • Availability for part-time remote work • Openness to B2B contractor collaboration

🏖️ Benefits

• Multi-month contract with strong extension probability • 0.5 FTE minimum, ramping toward 1.0 FTE as production scales • Structured handover and knowledge transfer from the outgoing architect • Opportunity to work on a production-stage AI program for a major US private-equity-backed client