Gen AI Developer

A high-growth organization in the Enterprise Generative AI and Applied Machine Learning sector building production-grade LLM services, conversational agents, and retrieval-augmented generation (RAG) solutions for enterprise customers. We deliver secure, low-latency GenAI features that combine vector search, prompt orchestration, and API-driven workflows. This is an on-site engineering role based in India focused on shipping scalable GenAI systems into production.

Primary Title: Generative AI Engineer

Role & Responsibilities

• Architect, implement, and deploy end-to-end GenAI features: embeddings ➜ vector indexing ➜ retrieval ➜ LLM orchestration for production use-cases.
• Build and integrate LLM workflows and agents using LangChain (or equivalent), OpenAI/Hugging Face APIs, and custom orchestration logic.
• Fine-tune, evaluate, and optimize models and embedding pipelines to improve relevance, latency, and cost (incl. quantization and batching strategies).
• Design and operate scalable vector search solutions (FAISS/Pinecone/Milvus) with efficient indexing, sharding, and query optimization.
• Containerize and productionize inference services with monitoring, CI/CD, observability, and GPU-aware deployment patterns.
• Collaborate with product, data, and ML teams to translate requirements into reliable GenAI features and document engineering best practices.

Skills & Qualifications

• Must-Have

• Python
• PyTorch
• Hugging Face Transformers
• Prompt engineering
• LangChain
• FAISS

• Preferred

• OpenAI API
• Model fine-tuning
• Docker

Benefits & Culture Highlights

• On-site role with access to GPU resources and hands-on production deployment experience.
• Fast-paced learning environment with opportunities to lead GenAI projects and shape technical direction.
• Competitive compensation, focused mentorship, and budget for technical training and conferences.