ML Engineer / LLM Specialist

Unabyss; Województwo mazowieckie; Remote; PLN 244,000 - 390,000; Full time

Benefits offered by this job

Fully remote

ESOPs planned

Sports benefits

Direct collaboration with CTO

Job summary

Unabyss is building a universal context layer for AI. We seek an Applied Researcher to design and implement a memory system, data pipelines, and retrieval mechanisms with privacy controls.

You will prototype architectures, compare approaches, and collaborate directly with the CTO to shape the product's core technical direction. You should have 2+ years in ML/NLP/LLM production, strong Python, and deep retrieval knowledge.

Qualifications

• 2+ years of professional experience building ML/NLP/LLM systems in production.
• Strong Python proficiency for research and production tasks.
• Deep understanding of retrieval architectures beyond basic RAG - hybrid search, structured extraction, re-ranking, query decomposition.
• Comfort with rapid prototyping - building POCs, running experiments, measuring results, iterating fast.
• Experience using AI coding tools as part of the workflow.
• Strong algorithmic thinking and ability to reason about trade-offs (precision vs recall, cost vs accuracy).
• Experience designing and evaluating ML pipelines end-to-end.
• Ability to work independently and drive research-to-production cycles.
• Fluent English (written and spoken).

Responsibilities

• Design and build a knowledge/memory system that structures user context for precise retrieval.
• Build data processing pipelines to enrich, classify, and structure information as it flows in.
• Design retrieval mechanisms that are cheap, accurate, and traceable to root sources.
• Implement permission-aware access control at the retrieval layer with per-app consent boundaries.
• Evaluate and compare architectural approaches through rapid prototyping and benchmarking.
• Design prompt engineering strategies and LLM pipeline architectures using commercially available models.

Skills

ML/NLP/LLM production

Python

Retrieval architectures

Prototyping & experiments

AI coding tools

Algorithmic thinking

ML pipelines

Independence & decision making

English proficiency

Job description

About Unabyss

We're building Unabyss - the universal context layer for AI. Users store all their context (background, expertise, preferences, goals) in one place, and any AI tool can access it via MCP and APIs. The user controls what gets shared, with whom, at what depth. We've just raised pre‑seed funding and are assembling the founding engineering team. This is the ground floor of a company building core infrastructure for the AI era.

Applied Researcher

• Mid to Senior
• Full‑time
• Remote / Hybrid (Warsaw or Cracow)

What You're Gonna Do

• Design and build a knowledge/memory system that structures user context for precise, traceable retrieval
• Build data processing pipelines that enrich, classify, and structure information as it flows in
• Design retrieval mechanisms that are cheap, accurate, and traceable to their root sources
• Implement permission‑aware access control at the retrieval layer - enforcing per‑app consent boundaries
• Evaluate and compare architectural approaches (knowledge graphs, hybrid retrieval, structured extraction) through rapid prototyping and benchmarking
• Design prompt engineering strategies and LLM pipeline architectures using commercially available models
• Collaborate directly with the CTO to shape the core technical direction of the product

What We Require From You

• 2+ years of professional experience building ML/NLP/LLM systems in production
• Strong Python proficiency
• Deep understanding of retrieval architectures beyond basic RAG - hybrid search, structured extraction, re‑ranking, query decomposition
• Comfort with rapid prototyping - building POCs, running experiments, measuring results, iterating fast
• Experience with AI‑first programming - using AI coding tools (Cursor, Claude Code etc.) as a core part of your workflow
• Strong algorithmic thinking and ability to reason about trade‑offs: precision vs. recall, cost vs. accuracy, latency vs. completeness
• Experience designing and evaluating ML pipelines end‑to‑end
• Ability to work independently, make design decisions, and drive research‑to‑production cycles with minimal supervision
• Fluent English (written and spoken)

What's Nice To Have

• Experience with knowledge graphs - construction, querying, integration with LLM pipelines
• Background in information theory or information retrieval research
• Experience with permission/access‑control systems at the data layer
• Familiarity with prompt engineering at scale - structured outputs, chain‑of‑thought, tool use
• Experience in early‑stage / small‑team environments
• Published research or open‑source contributions in relevant areas

What You'll Get

• €5,000-€8,000/month gross (€60k-€96k/year), calibrated to experience and location
• Fully remote with full flexibility - work from anywhere within CET ±2h
• ESOPs planned as the company scales - you're joining early enough to benefit
• Sports benefits
• Direct collaboration with the CTO - outsized influence on the product's core architecture
• A clear growth path: evolve into Head of ML/AI or deepen into a principal/staff track as the team grows
• The chance to help build something massive from the very beginning