Engineer

About Us

NeuraPlox is seeking an Engineer to build our AI Agent Platform for enterprise clients in regulated industries.

We are not building tutorial LLMs, vibe engineering, or demo RAGs that fall apart at 10k embeddings. We are building explainable AI with audit lineage, decision provenance, and pgvector at scale because our clients don't just want to explain their AI outputs – they must.

Investor-backed, Munich Region.

Responsibilities

What you will build with us:

• Production-grade AI Agent Platform with PydanticAI, LiteLLM, Langfuse
• RAG Pipelines with pgvector at scale (Multi-Tenant Isolation, Index Rebuild Strategy, Hybrid Search)
• Multi-Tenant Token Quota Service plus Eval Frameworks per Tenant
• MCP (Model Context Protocol) Tool Integration as First-Class Citizen
• Explainable Outputs, complete auditability from prompt to output for regulated industries
• Architectural decisions that hold up in banking, insurance, and pharmaceutical contexts

How we work:

• Eval-driven, not vibe-driven. Every agent change goes through an eval suite.
• ADRs for every relevant architectural decision, not buried in Slack threads.
• LLM calls are measured, not guessed - Langfuse from day one.
• Re-ranking, pgvector sizing, and retrieval quality are decided empirically.
• Direct line to the founding team, no layer of project managers in between.

Qualifications

What we are looking for:

• 5+ years of Python production engineering
• Real production LLM experience with tokens, latency, cost, and eval as daily reality
• RAG engineering with pgvector sizing and re-ranking, not just "I know LangChain"
• LangGraph, PydanticAI, or comparable agent framework used in production
• LiteLLM, Langfuse, MCP - or willingness to learn in 2 weeks

Tech Stack:

Python, FastAPI, PydanticAI, LangGraph, LiteLLM, Langfuse, pgvector, MCP, Kubernetes fundamentals.

Benefits

You want to finally work with like-minded, true professionals on a high-performance solution – not just something dictated from above. With us, you work according to technical best practices – not what looks good to management. Great team, a lot of freedom in your work. You decide, real impact!

What we offer:

• VSOP as an investor-backed startup for key positions
• Fully remote possible, residence in Germany - team development days approx. 1x/month in the Munich office
• You report directly to Christoph Knöll (Founder/CEO) and work closely with our Head of AI
• Senior hire for the AI layer, you shape the agent architecture, not "tune prompts"

CV plus 3 sentences why this role specifically. No cover letter template.

We read every application ourselves.