Location: Remote / India
Type: Full-time
Overview
We’re looking for a passionate AI Engineer with hands-on experience building LLM-powered tools, agents, or infrastructure. You’ll be working at the core of Puch’s multilingual AI assistant, a system designed to serve millions of users across India in 11 languages through WhatsApp, voice, and web.
If you’ve built LLM workflows, autonomous agents, or real-world NLP tools and want to tackle challenges in language, scale, and reliability, this role is your playground.
🛠 Responsibilities
- Build and deploy end-to-end LLM pipelines: data cleaning, training, fine-tuning, and fast inference.
- Architect multilingual & multimodal systems spanning text, voice, and images.
- Implement and optimize retrieval-augmented generation (RAG), embeddings, and hybrid search pipelines with vector databases.
- Extend LLMs with custom tools, APIs, and real-time tool-calling systems.
- Run offline and online experiments to improve accuracy, latency, and user satisfaction.
- Contribute to internal tools for evaluation, safety checks, logging, and observability.
✅ Requirements
- Strong experience with modern AI/ML libraries (PyTorch, Hugging Face Transformers, LangChain, OpenAI APIs).
- Deep understanding of LLMs: pretraining, fine-tuning, inference, and prompt engineering.
- Proven ability to ship production-grade AI systems end-to-end.
- Familiarity with vector databases and agent orchestration patterns.
- Bachelor’s degree in CS, AI/ML, or related field (or equivalent real-world experience).
💡 Bonus Points
- Experience with multilingual NLP or Indian language models.
- Contributions to open-source AI projects, research papers, or live demos.
- Knowledge of latency-sensitive AI systems or streaming inference optimization.
📩 How to Apply
If you’re excited to build cutting-edge multilingual AI systems that will be used by millions, we’d love to hear from you!
AI Engineer Job
🔎 Guidance for Candidates
- Share specific projects where you’ve built or deployed LLM-powered applications.
- If you’ve worked on multilingual or multimodal AI, highlight it — we value real-world impact.
- Links to GitHub, Hugging Face demos, or research contributions will give you a strong edge.
