# trg.recruitment (client undisclosed) — AI Retrieval & Relevance Engineer

| Field | Value |
|---|---|
| **Date found** | 2026-05-28 |
| **Company** | trg.recruitment (client undisclosed) |
| **Role** | AI Retrieval & Relevance Engineer |
| **Location** | EU Remote |
| **Salary** | $140,000 B2B via Deel |
| **Job URL** | https://www.linkedin.com/jobs/view/4417613600/ |
| **Status** | New |

---

## Company Research

Recruiting agency — client undisclosed.

---

## Job Summary

**What they do:** Undisclosed client (posted via trg.recruitment agency) — context suggests an AI product company building agent-facing retrieval and search infrastructure.

**The role:** Senior IC engineer owning the retrieval layer of an AI system — hybrid vector + keyword search, embedding pipelines, and re-ranking for LLM agent consumption.

**Core work:**
- Design and optimise hybrid retrieval systems (dense + sparse) using FAISS, Weaviate, Milvus, Pinecone, Elasticsearch
- Build embedding pipelines and re-ranking models to improve retrieval quality for AI agents
- Tune retrieval performance for latency and relevance at scale

**Stack:** FAISS · Weaviate · Elasticsearch · Milvus · Pinecone · Python · PyTorch · RAG · Hybrid search · Embedding models · Re-ranking

**Work style:** Fully remote EU-wide; B2B contractor engagement via Deel at $140k/year

---

## Score: 74%

| Dimension | Score | Justification |
|---|---|---|
| Agentic AI depth (25%) | 65% | Retrieval infrastructure for AI agents — strong RAG/vector search depth, but not multi-agent orchestration or LLM pipeline design itself |
| Tech fit (25%) | 70% | Strong vector DB and embedding stack overlap; PyTorch and Python match; no LangGraph/LangChain/CrewAI mentioned |
| Remote fit (25%) | 100% | Fully remote EU-wide — perfect fit |
| Company culture fit (15%) | 40% | Client is anonymous; agency posting removes visibility into actual company culture |
| IC/leadership balance (10%) | 90% | Pure IC senior engineer role with no management signals |
| **Final (weighted)** | **74%** | |

---

## Strengths

- Strong salary signal: $140k B2B — well above €100k floor (assuming EUR/USD parity ~1:1)
- Direct stack match on RAG and vector search infrastructure — core Luca expertise
- Fully remote EU-wide, no on-site requirement
- Pure IC role — no management drift

---

## Weaknesses & Risks

- Recruiting agency (trg.recruitment) posting for anonymous client — no visibility into actual company, culture, or stability
- B2B contractor structure via Deel — not a direct employment offer; no benefits, IR35-like considerations
- Lower agentic AI depth than ideal — retrieval infrastructure rather than multi-agent orchestration
- $140k is USD; actual EUR value depends on rate and contract terms

---

## Suggestions

- Highlight the RAG medical knowledge base project (43% retrieval improvement) as direct evidence of retrieval system optimisation
- Reference multimodal QA RAG system at cybersecurity role as production-scale vector search experience
- Request client identity before investing significant time — agency roles without client disclosure carry risk
- Clarify employment vs B2B contract terms and tax implications in Ireland

---

## Interview Tracker

| Stage | Date | Notes |
|---|---|---|
| Rejected | 2026-05-28 | Contract |
| Applied | | |
| Recruiter screen | | |
| Technical interview | | |
| Final round | | |
| Offer / Outcome | | |