Novumstate
is in the top 4% of German Real Estate Services Providers. We are a team of real estate owners and investors, with strong backgrounds in digital marketing, strategy and start-ups. Our vision is to transform the property management industry by combining state-of-the-art technology, first-class service, and comprehensive expertise.
We are looking for a results-driven
Python Developer
specializing in building
AI-powered automation workflows
using
LangChain
. Strong proficiency in document/email processing,
ETL pipelines
,
MongoDB
,
Chroma
, and data manipulation with
Pandas
. Bonus expertise in
Salesforce plugin development with Java
, enabling seamless integration with CRM workflows. Ideal for transforming unstructured communication into structured, actionable insights.
Your Responsibilities:
Email \& Document Parsing
:
Extract metadata, content, attachments from email servers or shared drives
Parse PDFs, Word docs, HTML, plain text using reliable libraries
Case Generation Pipeline
:
Transform raw unstructured inputs into structured, queryable "cases"
Use LLMs to classify, extract intent, and associate case metadata
Data Hydration \& Enrichment
:
Query MongoDB and external APIs (e.g., Salesforce) to enhance data completeness
Update or create Salesforce records via plugin interfaces if needed
AI Workflow Orchestration
(LangChain):
Implement step-based chains to analyze case data
Integrate Chroma vector searches for semantic enrichment
Use LLM reasoning to output decisions/actions
ETL Management
:
Build robust pipelines with retry logic, logging, and monitoring
Optimize large-scale data transformations using Pandas
Handle schema changes and maintain backward compatibility
Bonus: Salesforce Plugin Development
Java experience with Salesforce plugin/API development
Able to push/pull data to/from Salesforce for contextual case enrichment
Can work with Salesforce Events, Flows, or REST APIs from both Java and Python layers
Your required Technical Skills and Experiences:
Languages \& Frameworks
Python
(Advanced – automation, AI pipelines, API development)
Java (for Salesforce plugin/custom integration)
FastAPI / Flask (API layer)
Pandas (ETL \& data wrangling)
LLMs \& AI Tools
LangChain (Chains, agents, tools, retrievers, RAG architecture)
OpenAI / Anthropic LLMs
Prompt Engineering
Chroma (Vector store – semantic search, metadata filtering)
Named Entity Recognition (NER), Summarization, Classification
Data \& Storage
MongoDB
(primary data store – structured/unstructured data, case management)
Chroma
(vector search – for semantic document lookup)
Salesforce (data sync \& plugin development via Java-based integrations)
JSON, YAML, and nested data structure manipulation
ETL \& Data Pipelines
End-to-end pipeline building: extraction, transformation, and load
PDF, email, and file ingestion
Data hydration: merging case data with internal DBs, CRM, and APIs
Schedule and trigger-based processing
Why you'll love working here
Attractive salary:
up to $2500
depends on your experiences and skills
13th-month Salary bonus with Annual Salary Review or on excellent performance
Government Social Insurance, Unemployment Insurance for 100% Salary
Health Insurance and Annual Health Check-up
Full set of Working Devices Provided
Birthday gift, Team Bonding Party, Company Trip and Events
A possibility to attend on-sites and conferences in Germany, Europe.
Annual leaves: 15 days off and 01 Birthday Leave per year (exclusive of public holidays)
An open and dynamic working environment with opportunity to be part of innovation team and global projects
Nice office with free snacks and drinks in the centre of Hanoi at No. 1 Thai Ha St.
Working Time: Monday to Friday (from 9AM to 12AM and 1PM to 6PM)
Contact me at
hang.nguyen@novumstate.com
for any further information or sending me your CV directly there!