Defining how AI and finance work together — securely, intelligently, and at scale.
We at
Unique AI
are building a highly secure generative AI platform, tailored for the financial sector. Utilizing AI, LLM, agentic and Skills technologies, we aim to revolutionize the Financial industry with an AI Automated workforce. Our mission is to increase efficiency, improve alpha, reduce risk, and increase quality across everything we do. We offer an inclusive environment at Unique and we encourage all genders and all neuro-diversities to apply.
We're building an enterprise AI platform where knowledge ingestion is a foundational capability. It is how customer documents, files, and unstructured data enter the system so that AI assistants can search, retrieve, and reason over it.
We're looking for a
backend-focused tech lead
to own the technical direction of this platform end to end. This is
a hands-on technical leadership role
. You will set architecture, guide implementation across the core ingestion services, mentor engineers through design and code review, and drive improvements in reliability, throughput, retrieval quality, and maintainability.
7+ years of backend engineering experience
with strong expertise in
TypeScript
and
Node.js
Experience as a technical lead
for a backend or platform domain, with ownership of architecture, technical direction, and mentoring
Strong experience building ingestion or unstructured data pipelines
, ideally involving document parsing across formats such as PDF, Office documents, HTML, or email
Strong database, indexing, and retrieval experience
across
PostgreSQL
,
Elasticsearch
,
Qdrant
, or similar systems
Experience improving retrieval quality in production
using embeddings, vector search, or RAG-style retrieval systems
System design maturity
: you can design for scale, failure handling, service boundaries, and pragmatic trade-offs under real constraints
Multi-tenant SaaS experience
: you understand data isolation, tenant-scoped processing, and enterprise security requirements
Technical leadership:
Define and own the RAG platform’s architecture and standards, make trade-offed design decisions, drive high-impact backend improvements across the pipeline, and communicate a clear technical roadmap.
Hands-on backend engineering:
Build and evolve ingestion, processing, and retrieval services/APIs, strengthen async pipelines (RabbitMQ, retries, backpressure), enhance parsers, and optimize indexing on Qdrant/Elasticsearch for quality and latency.
Retrieval and document intelligence
: Partner with AI engineers to advance chunking, embeddings, metadata, and RAG patterns; integrate Python services for agentic workflows; improve retrieval via better indexing/enrichment/evaluation and adopt OCR/layout/table extraction when it moves the needle.
Technical leadership for the team
: Mentor and unblock engineers through reviews and pairing, elevate reliability/performance/observability/testing, and support hiring and onboarding without primary people-management duties.
Platform ownership:
Run production delivery via Helm/Kubernetes and ArgoCD GitOps, enhance observability with OpenTelemetry/Prometheus/logging/alerts, and enforce multi-tenant data isolation, security, and auditability end to end.
Leading Company
💪 A chance to be part of a leading company in a rapidly evolving industry
Innovative & Impactful Projects
🚀 Engage in groundbreaking projects within the Generative AI space. Contribute towards building the foundations enabling financial institutions to operationalize AI.
Ownership & Autonomy
🧠
We care about outcomes and the right solution crafted with clean code
Continuous Learning
🔄 AI is moving fast and we value engineers who keep learning and experimenting
Culture
🌿 A modern company with flat hierarchies that focuses on a people-oriented culture and places great emphasis on transparency and open communication
Hybrid set up
🧑💻🏢
Based in Berlin with flexibility for remote days