HamburgerMenu
hirist

Senior Generative AI Engineer - LLM/RAG

Tecfirst
4 - 9 Years
Bangalore

Posted on: 16/04/2026

Job Description

Role : Senior Gen AI Engineer

Location : Bengaluru, Karnataka

Experience : 4 - 7 Years

Notice Period : Max 30 Days

About the Company :


We are a high-growth, venture-backed startup reimagining billing and pricing infrastructure for the modern SaaS era. Founded by successful serial entrepreneurs with backgrounds at Google and Harvard, we are building the intelligence layer that helps companies manage complex, usage-based pricing models. We are looking for an engineer who moves fast, values reliability, and wants to build production-grade AI systems, not just prototypes.

The Role :


As a Senior Gen AI Engineer, you will own the AI vertical of our product. This is a high-stakes, high-visibility role where you will build features that enterprise clients depend on daily. You wont just be writing prompts; you will be designing robust backend architectures, agentic workflows, and end-to-end AI pipelines.

Key Responsibilities :


- Production AI Systems : Build and scale "CS Copilot," a real-time assistant for customer success teams involving STT pipelines and LLM suggestions.


- Document Intelligence : Develop LLM-powered features to extract structured, reliable data from unstructured enterprise documents.

- Agentic Workflows : Design and orchestrate multi-step AI agents using frameworks like LangGraph, CrewAI, or custom orchestration logic.

- RAG Pipelines : Architect advanced Retrieval Augmented Generation systems, including optimized chunking, embeddings, and retrieval strategies.

- Reliability & Evals : Build rigorous evaluation frameworks to measure accuracy, manage latency, optimize costs, and ensure graceful degradation.

- Full-Stack Ownership : While focused on the backend/AI layer, you will own features end-to-

end, including basic UI integration and API orchestration.

Mandatory Requirements :


- Experience : 4+ years in software development, with at least 2+ years of shipping AI/LLM features in production.


- Backend Expertise : Mastery of Python (FastAPI or Django) and building production-grade

backend services.


- AI Ecosystem : Hands-on experience with OpenAI, Gemini, or similar models, specifically focused on chaining, tool usage, and structured outputs.

- System Design : Strong coding and system architecture skills we are looking for a builder, not a researcher or prompt engineer.

- Start-up Pedigree : Previous experience in product-based startups (Series A to Series D).

- Reliability Mindset : Deep understanding of fallback handling, observability, and AI system

performance

Preferred Qualification :


- Education : Graduates from Tier-1 institutes (IITs, BITS, NITs, IIITs, or equivalent global universities).


- Advanced AI : Experience with fine-tuning (LoRA/QLoRA) or open-source deployment (vLLM,

Ollama).


- Frontend : Ability to contribute to the frontend (React or similar).

Perks & Benefits :


- Competitive Compensation : High-growth salary range + Performance-linked variables.

- Equity : ESOPs for long-term wealth creation.

- Health & Wellness : Comprehensive health insurance and generous vacation policy.

- Growth : Dedicated learning and development budget, team offsites, and a high-performance culture.


info-icon

Did you find something suspicious?

Similar jobs that you might be interested in

Loading chat...