Experience: 5.00 + years
Salary: Confidential (based on experience)
Expected Notice Period: 15 Days
Shift: (GMT+05:30) Asia/Kolkata (IST)
Opportunity Type: Remote
Placement Type: Full Time Contract for 12 Months(40 hrs a week/160 hrs a month)
(*Note: This is a requirement for one of Uplers client - WE)
What do you need for this opportunity
Must have skills required:
Postgres, Pydantic, Agentic AI, Ci/Cd Pipelines, Docker, Machine Learning, Python, Redis
WE is Looking for:
We're building AI that makes real estate investing faster, smarter, and more defensible. If you live at the intersection of agentic systems, messy data, and genuine product impact — keep reading.
About
Client is an early-stage AI platform helping real estate investors underwrite deals with speed and confidence.
Our core product is a LangGraph-based agentic system that:
- Ingests deal flow from email
- Automatically pulls in market and public-record data
- Surfaces structured underwriting reports with risk flags and go/no-go signals — in minutes, not days
We're a small, technical founding team that moves fast. You'll have real ownership over architecture decisions, not just tickets.
The problems are hard:
- County websites that haven't been updated since 2009
- PDFs that resist parsing
- Permit histories scattered across a dozen siloed systems
If that sounds interesting, we should talk.
THE ROLE
We're looking for a full-stack AI engineer who can own the entire vertical — from raw data ingestion to production-grade features that users rely on every day.
You're comfortable pushing clean, well-tested code to production, not just prototyping in notebooks.
You have genuine familiarity with ML concepts and tooling:
- You understand the difference between a fine-tuned model and a prompted one
- You know when to reach for scikit-learn vs. a neural approach
- You have a point of view on model evaluation
What You'll Do
- Extend and harden our LangGraph agentic pipeline
- Own a critical new workstream: building a robust, resilient data ingestion layer
- Work with data sources like:
- County assessors
- Permit offices
- MLS feeds
- Zoning databases
- Alternative investor-relevant datasets
- Own automated testing infrastructure:
- Write and deploy testing agents
- Validate data quality, pipeline integrity, and output accuracy
- Work directly with founders to ship features to production
EXAMPLES OF SOME THINGS YOU'LL DO
- Extend and optimize our LangGraph agentic system — designing new nodes, edges, and human-in-the-loop flows that improve deal analysis reliability and coverage
- Build and maintain web scrapers and data pipelines targeting:
- County assessor sites
- Permit portals
- Zoning maps
- Deed records
- Fragmented public data sources across 3,000+ U.S. counties
- Integrate structured and unstructured third-party data feeds (CoStar, ATTOM, Rentcast, Zillow-adjacent APIs, MLS data) into the underwriting agent's context
- Design resilient extraction strategies for hostile environments:
- CAPTCHAs
- Rate limits
- JavaScript-heavy SPAs
- Inconsistent schemas
- Develop and fine-tune LLM-powered parsing layers to convert:
- PDFs
- HTML tables
- Scanned records
- → into clean, structured data
- Build and operate automated testing agents:
- Agentic test harnesses
- Continuous validation of pipelines, scrapers, and outputs
- Instrument pipelines with observability tooling (LangSmith, Langfuse, or equivalent)
- Build monitoring for:
- Data freshness
- Agent accuracy
- Source reliability
- Establish eval frameworks and regression suites to catch:
- Agent drift
- Prompt degradation
- Data schema breakage
- Collaborate on prompt engineering to improve underwriting outputs and risk flag generation
- Contribute to data architecture:
- Schema design
- Caching strategies
- Data normalization
What We're Looking For
AGENTIC & ML
- LangGraph or comparable frameworks (CrewAI, AutoGen)
- LangChain ecosystem (tools, memory, callbacks)
- Prompt engineering & structured outputs
- RAG pipeline design
- LLM observability & evaluations
- Automated testing agents & eval harnesses
DATA & SCRAPING
- Scrapy, Playwright, Selenium, or Puppeteer
- Anti-bot evasion & proxy management
- PDF & document parsing (pdfplumber, LlamaParse)
- REST + GraphQL API integration
- SQL (Postgres) & NoSQL data modeling
ENGINEERING
- Python (primary) — async, type-annotated
- Cloud infrastructure: AWS or GCP (serverless, queues)
- Containerization with Docker
- CI/CD pipelines & automated testing infrastructure
- Git-based workflows & code review culture
WORKING STYLE
- Operates autonomously — drives work to completion
- Ownership mentality — treats the product like it's yours
- Comfortable with ambiguity in an early-stage environment
- Strong written async communication
- Pragmatic — ships, then refines
- Curious about real estate or proptech
NICE TO HAVE
- Python, LangGraph, Playwright, Scrapy
- OpenAI / Anthropic APIs
- pytest / eval agents
- Postgres
- AWS / GCP
- LangSmith
- Pydantic
- FastAPI
- Redis
- Docker
Domain Experience (plus)
Real Estate Data
- Experience with data vendors:
- ATTOM
- CoStar
- Rentcast
- FEMA flood maps
- Zoning APIs
- Familiarity with ACORD forms or insurance data
- Prior work at a proptech or fintech startup
ML Modeling
- Hands-on experience building and deploying predictive models
- Familiarity with Automated Valuation Models (AVMs)
Includes:
- Feature engineering from:
- Public records
- Transaction data
- Sales comps
- Cap rates
- Rent rolls
- Model selection:
- Gradient boosting
- Hedonic regression
- Neural approaches
- Ability to serve predictions reliably at scale
- Experience with geospatial features:
- Proximity scores
- Submarkets
- Walkability signals
Agentic Workflows
- Experience building human-in-the-loop systems
- SMS/email-triggered agentic pipelines
- LLM systems with:
- Automated regression testing
- Continuous evaluation pipelines
How to apply for this opportunity
- Step 1: Click On Apply! And Register or Login on our portal.
- Step 2: Complete the Screening Form & Upload updated Resume
- Step 3: Increase your chances to get shortlisted & meet the client for the Interview!
About Uplers:
Our goal is to make hiring reliable, simple, and fast. Our role will be to help all our talents find and apply for relevant contractual onsite opportunities and progress in their career. We will support any grievances or challenges you may face during the engagement.
(Note: There are many more opportunities apart from this on the portal. Depending on the assessments you clear, you can apply for them as well).
So, if you are ready for a new challenge, a great work environment, and an opportunity to take your career to the next level, don't hesitate to apply today. We are waiting for you!
