zenskar
Website:
zenskar.com
Job details:
About the Role
We are looking for a Senior GenAI Engineer to own and build the AI layer of our product — the features that make our platform truly intelligent.
This is not a research or prompt-only role. You will design and ship production-grade AI systems where reliability, observability, and evaluation frameworks are as critical as model performance.
You will own the full vertical — from model → pipeline → backend → UI.
What You’ll Do
- Build and own AI-powered copilots (real-time assistants with STT, transcription, and LLM suggestions)
- Develop LLM-based document understanding systems to extract structured insights from unstructured data
- Design and maintain evaluation frameworks to measure and improve AI system performance
- Architect and implement end-to-end AI pipelines (RAG, chaining, tool usage, structured outputs)
- Build and optimize agentic workflows (multi-step reasoning, tool orchestration)
- Drive model selection, experimentation, and integration decisions
- Ensure AI system reliability — observability, latency optimization, fallback handling
- Own AI feature UIs (working across backend + frontend layers when needed)
- Collaborate closely with product, engineering, and customer-facing teams
Impact You’ll Make
- Define how AI is experienced by end users — your features will be core to the product
- Build systems that directly influence enterprise adoption and buying decisions
- Establish best practices around AI reliability, evals, and production readiness
- Move beyond demos — build AI systems that actually work at scale
Ideal Candidate
- 4–7 years of experience in software engineering, with 2+ years in AI/LLM-based systems
- Strong backend engineering experience using Python (FastAPI / Django preferred)
- Hands-on experience building LLM applications (OpenAI / Gemini / similar)
- Strong understanding of RAG pipelines (chunking, embeddings, retrieval)
- Experience designing end-to-end AI systems (chaining, tools, structured outputs)
- Experience with agentic frameworks (LangGraph, CrewAI, or custom orchestration)
- Proven track record of shipping AI features in production (not just POCs)
- Strong system design and coding skills
- Experience working with APIs, backend services, and integrations
- Understanding of AI reliability (latency, cost optimization, fallback strategies, evals)
Good to Have
- Experience with fine-tuning (LoRA / QLoRA)
- Exposure to open-source model deployment (vLLM, Ollama)
- Basic frontend experience (React or similar)
- Background in product startups / high-growth environments
- Tier-1 education (IITs, BITS, NITs, IIITs, top global universities)
Why Join Us
- Build real-world AI systems used by enterprises daily
- High ownership — end-to-end feature control
- Work on cutting-edge GenAI problems (RAG, agents, copilots)
- Fast-paced startup environment with high visibility & impact
- Strong engineering culture focused on quality and scalability
Perks & Benefits
- Competitive compensation + performance-based variable
- ESOPs (for full-time roles)
- Health insurance
- Learning & development budget
- Generous leave policy
- Team offsites & events
- Maternity & paternity benefits
- Company laptop
- Friday game nights
Click on Apply to know more.