---
title: 'AI Architect (Voice AI) at Neurons Lab'
canonical: 'https://feeny.ai/job/ai-architect-voice-ai-neurons-lab-poland-c1skkb3c8gj1'
type: 'job'
last_seen: '2026-09-08'
---

# AI Architect (Voice AI) at Neurons Lab

- **Company:** Neurons Lab
- **Location:** Poland
- **Employment:** contract
- **Work type:** remote
- **Posted:** 2026-08-26
- **Last confirmed live:** 2026-09-08
- **Apply:** https://jobs.ashbyhq.com/neurons-lab.com/9d21a752-735f-414c-9bfa-44564a42a3cf

## Job description

ABOUT THE PROJECT (DESCRIPTION, DURATION, STAGE)

The client is the largest US network of in-home veterinary hospice and end-of-life care. A major US private-equity sponsor drives the AI program and plans more projects across its portfolio.

We built a real-time voice copilot for their Veterinary Care Coordinators (VCCs). The copilot listens to live calls with pet families. It extracts appointment and clinical fields while the call runs. It fills the client's scheduling system through a Chrome extension. A second workstream, the Vet Visit Copilot, sends each vet an AI pre-visit briefing by email (Amazon SES).

Next is the production phase.

Stage: production SOW in executive alignment; start expected September 2026.

Duration: multi-month, with strong extension probability. 0.5 FTE minimum; ramp toward 1.0 FTE as production scales.

Why the role is open: the current architect moves to another strategic build. He stays at 0.15–0.2 FTE for supervision and knowledge transfer during ramp-up, so the new architect gets a structured handover.

## OBJECTIVE

- Own the technical architecture and delivery of the voice copilot from validated PoC to production
- Hit the bar this client tests against: latency, accuracy, concurrency, and cost
- Keep expectations aligned: production polish is in scope now; protect the team from silent scope creep
- Transfer knowledge continuously to the client's team and Neurons Lab engineers

## AREAS OF RESPONSIBILITY

## TECHNICAL ARCHITECTURE & HANDS-ON IMPLEMENTATION

- Own the full pipeline: streaming speech-to-text, LLM field extraction, Chrome-extension delivery, and AWS infrastructure
- Drive latency work: cut P95 from ~6s toward ~2s; remove post-processing corner cases (occasional ~1min lag on one field type)
- Run model A/B tests (current pair: Claude Haiku vs GPT Luna) with golden-set evaluation for phonetic name and email accuracy
- Own evaluation and cost: Langfuse traces, accuracy dashboards, real per-call cost from live calls, and an optimization plan
- Harden for production: 5–10+ concurrent calls, strict data isolation between users, monitoring, alerting, and safe rollback
- Ship epics end to end (example: the SES email briefing service); always keep a demo fallback so a live session never fails

## WORKING WITH CLIENT STAKEHOLDERS

- Front technical discussions with a meticulous client; VCCs test edge cases and expect production quality
- Present concrete system behavior, with numbers — this account rewards evidence, not slides
- Hold the scope line: tie every feedback item to the SOW; route roadmap items (learning loop, persistent memory) to future phases
- Keep internal discussions internal; all client-facing materials pass ADM review before sending

## TEAM & KNOWLEDGE

- Lead the AI Engineer and the pod: set tasks, review output, unblock fast
- Absorb the handover from the outgoing architect (0.15–0.2 FTE supervision window) and become independent fast
- Run knowledge-transfer sessions; the project must have no single point of failure
- Support the production SOW with estimates and architecture options when the account team asks

## SKILLS

- Real-time voice pipelines: streaming STT, turn handling, low-latency LLM inference — hands-on
- LLM engineering: prompt engineering, structured extraction, guardrails, model A/B evaluation
- Observability and evals: Langfuse or similar; golden datasets; latency, accuracy, and cost dashboards
- AWS: Bedrock, serverless patterns, SES; token economics and per-call cost engineering
- Full-stack pragmatism: strong Python; enough TypeScript / Chrome-extension knowledge to own the integration
- Clear spoken and written English for demanding US executives

## KNOWLEDGE

- Contact-center / agent-assist patterns and metrics (handle time, cost per call, concurrency)
- Production LLM operations: load testing, data isolation, incident handling
- Nice to have: empathy-sensitive domains (healthcare, veterinary, insurance) and PE-sponsored rollouts

## EXPERIENCE

Key characteristics (screen for all four):

1. Voice AI in production — mandatory. Shipped at least one real-time voice or speech product to real users (agent assist, voice bot, live transcription copilot). Candidates will demo real artifacts at the interview.
2. 6+ years hands-on AI/ML engineering, with strong recent LLM production practice
3. Latency and reliability record. Can show measured P95 reductions and concurrency fixes on a live system
4. Consulting / client-facing seniority. Calm and precise under detailed UAT scrutiny; manages expectations well

Nice to have:

- Chrome extension delivery; telephony / streaming stacks (Amazon Connect, Twilio, LiveKit)
- Langfuse in production
- US client experience with Eastern-time overlap

## About Neurons Lab

## Company Overview
- **One-liner**: Neurons Lab is an AI engineering partner that helps Financial Services organizations adopt AI and build production-grade agentic systems, from initial use case definition through deployment and continuous delivery.
- **Entity Type**: Private (Bootstrapped / Self-funded boutique firm)
- **Headquarters**: London, United Kingdom (International House, 64 Nile Str, London, N1 7SR)
- **Founded**: 2019
- **Founders**: Igor Sydorenko (CEO & Co-Founder) and Alex Honchar (CTO & Co-Founder)

## Core Business
- **Primary industry/industries**: AI Engineering & Consulting, focused exclusively on Financial Services (banking, capital markets, wealth management, insurance)
- **Target customers**: B2B — Fortune 500 financial institutions, large banks, wealth management firms, insurance companies, and adjacent regulated industries
- **Mission or purpose statement**: To help Financial Services organizations move from AI-curious to AI-enabled by building capability and deploying systems across core workflows — translating AI ambition into secure, scalable solutions that deliver commercial value.

## Products & Services
- **Custom AI Agents**: Deploy custom AI agents from discovery through production, enabling automation across core workflows with full auditability, traceability, and governance controls built in from the start. Decision logic is aligned with business rules and policies, designed for high-value workflows where accuracy, compliance, and scale are critical.
- **AI Training & Enablement**: Build AI fluency across teams, from engineering to the C-suite, through hands-on training grounded in the client's core workflows. Separate tracks for business and technical teams, with governance, compliance, and risk embedded from the start.
- **Continuous AI Delivery**: Post-deployment support with Forward-Deployed Engineers working alongside client teams to ensure systems continue to evolve. Governance, monitoring, and performance tracking are built in from the start, with AI adoption compounding across workflows over time.

## Market Standing
- **Valuation/Market Cap**: Not publicly available (private, self-funded boutique firm)
- **Key Metric**: Total Funding — Not disclosed (bootstrapped); the team reports 100+ AI implementations since 2019, including with Fortune 500 firms, and a team of 50+ AI engineers, architects, and analysts across Europe
- **Notable Investors/Partners**: Anthropic (partner), AWS (Advanced Partner, among first 15 to achieve AWS GenAI Competency in Agentic AI), Google Cloud (Partner)
- **Growth Signals**: Achieved AWS AI Competency in the Agentic AI category; named clients include HSBC (aligned 50+ senior leaders on AI deployment and governance) and Visa (scaled marketing operations across 9+ markets with LLM-based content system); works with leading Asian banks on agentic AI assistants for relationship managers

## Competitive Advantages
- **FSI Domain Expertise**: Deep specialization in Financial Services (banking, capital markets, wealth management, insurance) means no translation layer between business intent and technical execution. Compliance, governance, and risk are built into system design from the start.
- **Embedded Co-Creation**: Unlike traditional consultancies, they co-create with client teams through embedded delivery, working alongside internal stakeholders to transfer knowledge and expand impact from inside the organization.
- **Accelerated Delivery**: Pre-built FSI agent components and proven deployment patterns allow delivery of working, production-grade systems in weeks rather than months.
- **Boutique Senior Teams**: Small, senior teams (50+ engineers/architects) rather than large junior-heavy teams, enabling high-quality, fast execution.

## Strategic Focus
- Expanding agentic AI adoption within regulated financial environments, focusing on production-grade systems that operate within existing governance frameworks
- Building on partnerships with Anthropic, AWS, and Google Cloud to deliver cutting-edge AI solutions
- Deepening presence in wealth management, retail/corporate banking, private banking, SME banking, and insurance segments
- Scaling through a two-tier talent model (Core Team + Talent Network) to remain agile while growing

## Why Work Here
- **Remote-first culture**: Work from anywhere, with flexible hours — "design your day" philosophy
- **Benefits**: Unlimited PTO, flexible schedule, work on projects incorporating the latest AI technology (Anthropic, AWS, GCP)
- **Culture**: 7 guiding principles including ownership, genuine connections, and leadership development. Small, senior teams with high autonomy and low bureaucracy
- **Growth**: Opportunity to work on cutting-edge agentic AI for Fortune 500 financial clients, with clear paths to leadership roles
- **Team structure**: Two collaboration options — Core Team (full-time, benefits-eligible) or Talent Network (project-based, minimum 0.33 FTE)
- **Interview process**: Fast, streamlined — application → screening interview → validation interview → qualification interview → reference check

## Sources
1. [neurons-lab.com](https://neurons-lab.com/about/)
2. [neurons-lab.com](https://neurons-lab.com/)
3. [neurons-lab.com](https://neurons-lab.com/careers/)
4. [jobs.ashbyhq.com](https://jobs.ashbyhq.com/neurons-lab.com)
5. [neurons-lab.com](https://neurons-lab.com/careers/core-team/)

## Other roles at Neurons Lab

- [AI Governance Trainer (UK)](https://feeny.ai/job/ai-governance-trainer-uk-neurons-lab-united-kingdom-j5f66ct54k35) — United Kingdom
- [AI Architect / Tech Lead (mahjong game)](https://feeny.ai/job/ai-architect-tech-lead-mahjong-game-neurons-lab-poland-n3hs5h6ks68q) — Poland
- [Chief of Staff / COO](https://feeny.ai/job/chief-of-staff-coo-neurons-lab-poland-kv2zvem9we6h) — Poland
- [Data Engineer (UA/RU Language speaking)](https://feeny.ai/job/data-engineer-ua-ru-language-speaking-neurons-lab-poland-3dy117s3b1pz) — Poland
- [AI Analyst](https://feeny.ai/job/ai-analyst-neurons-lab-poland-q2mt5mxp7x2h) — Poland
- [Head of BFSI Solutions](https://feeny.ai/job/head-of-bfsi-solutions-neurons-lab-poland-k5wr8shvyys8) — Poland
- [Business Development / Sales Manager, FSI](https://feeny.ai/job/business-development-sales-manager-fsi-neurons-lab-united-kingdom-d5n6jjmttga4) — United Kingdom
- [Technical AI Engagement Lead](https://feeny.ai/job/technical-ai-engagement-lead-neurons-lab-poland-basa2gkjn6td) — Poland
- [AI Business Analyst / Product Manager](https://feeny.ai/job/ai-business-analyst-product-manager-neurons-lab-poland-r9fmkt8pj3d0) — Poland
- [AI Tools Trainer (freelance / project-based)](https://feeny.ai/job/ai-tools-trainer-freelance-project-based-neurons-lab-ukraine-ms7bydzh95cb) — Ukraine