About the Role:

We are looking for a highly skilled Senior GenAI Engineer to build and scale production-grade AI systems that enterprise customers rely on daily.

This is not a research-only or prompt-engineering role. You will own end-to-end AI features from model integration and backend pipelines to user-facing product experiences. The ideal candidate is a strong engineer with deep hands-on experience building reliable AI/LLM-powered systems in production environments.

If you enjoy building real-world AI products with high ownership, fast iteration, and direct business impact, this role is for you.

What You'll Do:

- Build and own AI-powered product experiences used by enterprise customers

- Develop real-time AI copilots using LLMs, speech-to-text pipelines, transcription systems, and intelligent workflows

- Build document intelligence features that extract structured insights from unstructured enterprise data

- Design and maintain scalable RAG pipelines using embeddings, chunking, retrieval, and orchestration frameworks

- Build end-to-end AI systems including backend services, APIs, integrations, and frontend-facing features

- Own AI reliability, observability, evaluation frameworks, latency optimization, and fallback handling

- Drive architecture and model selection decisions across OpenAI, Gemini, and open-source ecosystems

- Work closely with product and engineering teams to ship impactful AI features quickly and reliably

Required Skills & Experience:

- 5+ years of software engineering experience

- 2+ years building GenAI / LLM-based applications in production

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

- Hands-on experience with OpenAI, Gemini, Claude, or similar LLM ecosystems

- Strong experience with:

1. RAG pipelines

2. Embeddings & vector databases

3. Prompt workflows & structured outputs

4. Agentic AI systems

5. LangGraph / CrewAI / custom orchestration frameworks

6. AI system reliability & evaluations

- Strong coding, system design, and debugging skills

- Experience shipping scalable AI products, not just POCs or experiments

- Experience working in product companies or fast-paced startups

Good to Have:

- Experience with LoRA / QLoRA fine-tuning

- Exposure to vLLM, Ollama, or open-source model deployment

- Frontend exposure with React or similar frameworks

- Candidates from Tier-1 institutes preferred (IITs, BITS, NITs, IIITs, top global universities)

Ideal Candidate:

- Strong product-thinking mindset

- Comfortable working with ambiguity and ownership

- Passionate about building reliable AI systems, not just demos

- Able to balance speed, scalability, cost, and user experience

- Excited to work in a high-impact startup environment