Job Details
Experience: 5+ years; Salary: Confidential; Notice Period: 7 Days; Shift: Asia/Kolkata (IST); Opportunity Type: Remote; Placement Type: Full Time Contract (6 Months, 40 hrs/week, 160 hrs/month).
About Us
We are a semantic intelligence platform that transforms unstructured organisational data into queryable knowledge graphs powered by agentic AI. We serve enterprise clients across pharma, finance, and regulated industries — helping them unlock institutional knowledge through Graph RAG and multi‑agent AI systems.
The Role
You’ll be a key contributor to our backend — working across ETL pipelines, FastAPI services, and the agentic AI workflows that power our intelligence layer. You’ll collaborate closely with the CTO and a small senior team, contribute to architecture discussions, and bring your own thinking to the problems we’re solving.
What You’ll Work On
- Build and maintain FastAPI services powering our multi‑tenant backend
- Develop Python ETL pipelines that ingest and transform unstructured data into knowledge graphs
- Write well‑tested, production‑grade code with Pytest across unit, integration, and pipeline levels
- Use Pydantic for schema design, validation, and structured LLM output handling
- Contribute to the agentic AI layer — tool definitions, orchestration logic, LLM integration
- Collaborate on Neo4j data modeling and participate in architecture discussions
What We’re Looking For
- 5+ years Python in production environments
- Strong FastAPI and async Python experience
- Solid Pydantic v2 proficiency
- Test‑driven mindset with comprehensive Pytest coverage
- Experience building ETL or data processing pipelines
- Familiarity with LLM APIs (OpenAI, Anthropic, or similar)
- Collaborative, communicative, and comfortable in a fast‑moving startup environment
Nice to Have
- Neo4j / Cypher
- LangGraph
- RAG / vector databases
- Regulated industry background
- Multi‑tenant SaaS
Technical Stack
- Python
- FastAPI
- Pydantic
- Pytest
- Neo4j
- LangGraph
- OpenAI API
- AWS
- Docker
How We Work
- ClickUp for tasks
- Slack for communication
- Google Meet for calls — async‑first, minimal meetings, no micromanagement. Small team means your contributions ship fast and your impact is visible.
Application Process
- Step 1: Click “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.
If you’ve built production Python systems, care about clean architecture, and want to contribute to AI infrastructure that enterprises actually use — we’d like to hear from you.