About the Role :

Were hiring a Senior GenAI Engineer. This is a product engineering role, not research or prompt engineering. You will build production-grade AI systems that enterprise customers rely on daily where reliability, observability, and evaluation frameworks matter as much as model capability.

You will own the full stack of AI features from model ? pipeline ? UI.

What Youll Do :

- Build and own AI-powered product features end-to-end

- Develop CS Copilot real-time assistant with STT, transcription, and LLM suggestions

- Build document understanding systems (extract structured data from unstructured inputs)

- Design and implement RAG pipelines (chunking, embeddings, retrieval, orchestration)

- Build agentic AI systems (multi-step workflows, tool usage, orchestration frameworks)

- Own AI feature UIs (not just backend/model integration)

- Define and maintain evaluation frameworks to measure AI performance and catch regressions

- Drive model selection, cost optimization, and latency trade-offs

- Ensure AI system reliability observability, fallback mechanisms, graceful degradation

- Collaborate with product, engineering, and customer success to build usable, trusted AI features

What Were Looking For

Must-Have

- 4 to 7 years of software engineering experience

- 2+ years building LLM / GenAI applications in production

- Strong backend development experience using Python (FastAPI / Django preferred)

- Hands-on experience with LLMs (OpenAI, Gemini, or similar) in real-world applications

- Strong experience with RAG systems (embeddings, chunking, retrieval pipelines)

- Experience building agentic workflows (LangGraph, CrewAI, or custom orchestration)

- Experience designing end-to-end AI pipelines (chaining, structured outputs, tool usage)

- Strong understanding of system design, APIs, and backend services

- Experience shipping production-grade AI features (not just POCs)

- Understanding of AI system reliability (latency, cost, fallback handling, evals)

Good to Have :

- Experience with fine-tuning (LoRA / QLoRA)

- Experience deploying open-source models (vLLM, Ollama)

- Exposure to frontend development (React or similar)

- Experience in fast-paced product startups (Series AD)

Why Join Us :

- Own and define the AI layer of a fast-growing SaaS product

- Build high-impact, customer-facing AI features used by enterprise clients

- Work on real-world AI systems, not demos or experiments

- High ownership with direct collaboration with founders and product teams

- Opportunity to shape AI engineering standards (evals, reliability, observability)

Perks & Benefits :

- Competitive compensation + Performance-based variable

- ESOPs

- Health insurance

- Generous leave policy

- Learning & development budget

- Team offsites & events

- Maternity & paternity benefits

- Company laptop

- Team engagement activities

Location : Bangalore (In-office / Hybrid depending on policy)