[Hiring] Backend + GenAI Engineer @ Prayaan Capital — LangChain + FastAPI, Bangalore

Prayaan Capital
Bangalore

We're Prayaan Capital — an RBI-registered NBFC building AI-native credit infrastructure for MSMEs in India. Backed by Peak XV. Our leadership team has scaled MSME lending to ₹10,000 Cr+ AUM before doing this.

We're hiring a Backend + GenAI Engineer to join an early, small engineering team in Bangalore.

What you'll build:

• RAG pipeline over real credit decisioning cases, vector-indexed and queryable by LLM — this feeds our core credit engine
• Smart document extraction for KYC (Aadhaar, PAN, bank statements) using LLMs
• STT pipeline for collections call analysis integrating Sarvam/AssemblyAI
• Vendor facade layer normalizing responses across multiple KYC and STT providers with health monitoring and failover
• Async processing pipelines for long-running AI tasks

Stack: FastAPI, LangChain, Pinecone/Weaviate, Anthropic/OpenAI APIs, Node.js or Java for core backend support

Who we're looking for:

• 2–5 years backend engineering with strong Python proficiency
• Hands-on FastAPI and LangChain experience
• Has shipped something with LLMs in production — or demonstrably close to it
• Comfortable with ambiguity, iterates fast, cares about what actually works in production
  
  

  Bonus if you have: vector DB experience, STT/NLP pipeline work, prompt engineering discipline, MLOps exposure

  Compensation: ₹20–25L | Bangalore (in-office)
  
  

  Send in your applications with the following: 

  Along with your resume, include a short note (200–300 words) answering:

  • What's the most interesting LLM or AI integration you've built, and what surprised you in production?
  • Why does building AI infrastructure inside a regulated financial services company interest you?

  GitHub or portfolio links welcome.