Senior Backend/AI Engineer

Senior Backend/AI Engineer

Remote (CET ±4h) | 20-25k PLN net/month B2B

The Problem

Sales teams spend hours digging through news, LinkedIn, and databases looking for the right moment to reach out.

A company just raised funding. A VP just changed jobs. A competitor just expanded into a new market.

These signals exist - but finding them manually doesn’t scale.

ZYNT surfaces buying signals automatically. We are building multi-stage AI pipeline that processes thousands of sources, extracts what matters, and delivers actionable intelligence to sales teams in real-time.

The technical challenge:

Making AI reliable and cost-effective at scale. Utilizing APIs, NLP and LLM orchestration. Entity extraction, relevance scoring, semantic deduplication, and explainability. The kind of system where 85% accuracy isn’t good enough.

What You’ll Own

Our AI pipeline - the core intelligence layer that makes ZYNT valuable.

In your first month:

• Deep-dive into our multi-stage AI pipeline

• Audit current scoring and classification - find the gaps

• Ship your first improvement to signal quality

In your first quarter:

• Own signal quality end-to-end (scoring, classification, deduplication)

• Build semantic search across our growing signal database

• Improve entity extraction and relationship mapping

• Optimize LLM costs without sacrificing quality

Where we’re heading:

We want ZYNT to understand industries, not only individual signals - patterns across markets, sentiment shifts, and the “why” behind what matters.

Building auto-learning capabilities that make the system smarter over time.

The Stack

• Languages: TypeScript (primary), Python

• AI/ML: LLM APIs (OpenAI, Gemini), embeddings, vector search, NLP libraries

• Data: PostgreSQL, pgvector, Prisma

• Observability: Langfuse, structured logging

• Infrastructure: Background job orchestration, observability, Cloud

Who You Are

Must have:

• 4-8 years backend engineering experience

• 2+ years owning production AI/ML systems (building systems that work reliably at scale)

• TypeScript and/or Python fluency

• Experience with LLMs, embeddings, or NLP in production

• PostgreSQL proficiency

• Fluent Polish and English (C1+) - our customers and team speak both

The attitude:

• You see a problem, propose a solution, and ship it

• “85% accuracy” bothers you - you want 95%+

• You think about cost per API call without being asked

• You debug production issues when you spot them

Nice to have:

• Startup or 0→1 experience

• Entity extraction, knowledge graphs, semantic search

• Prompt engineering and LLM optimization

• MLOps / model monitoring

• Multi-tenant SaaS background

Red flags (not for you if):

• You prefer research over production systems

• You need detailed specs before starting

• “That’s not my area” is in your vocabulary

Why Join Now

You’d be one of our first engineering hires.

• Early-stage, real ownership: Small team, big problems, no bureaucracy

• Shape everything: Architecture, processes, culture - it’s all being built

• Customers using the product daily: We’re past the “will anyone use this” phase

• Visible impact: Your work directly enables everything else

How We Work

• Ship daily. We deploy to production constantly

• Founder-level ownership. You own outcomes, not tasks

• Direct customer access. You’ll hear what users need firsthand

• Outcomes, not hours. We care what you ship, not when you’re online

The Details

• Compensation: 20-25k PLN net/month (B2B)

• Equity: Discussed during process

• Location: Remote, CET ±4 hours overlap required

• Office: Optional access to Warsaw space

• Start: January-February 2026

Interview Process

1. Intro call - mutual fit check

2. Technical conversation - your experience, our challenges

3. Practical task - real problem, reasonable scope

4. Founders conversation - culture, vision, your questions