Senior AI/ML Engineer – Generative AI & LLMs

• Strong proficiency in Python
• FastAPI for building scalable backend APIs
• PostgreSQL and Redis
• LangGraph for building AI agents and workflows
• LangSmith and Langfuse for LLM evaluation, tracing, and observability
• Docker & Docker Compose for containerization and deployments
• Experience building production-ready RAG (Retrieval-Augmented Generation) pipelines
• Hands-on experience with Qdrant or other vector databases (Pinecone, Weaviate, Milvus, ChromaDB, FAISS)
• Strong understanding of embeddings, semantic search, chunking strategies, hybrid search, reranking, and retrieval optimization
• Experience deploying and maintaining AI applications on Linux servers or cloud infrastructure
• Git and modern software development practices

• Build scalable AI/LLM applications and backend services.
• Design, develop, and optimize production-grade RAG pipelines.
• Develop AI agents and workflows using LangGraph.
• Integrate and optimize LLMs from OpenAI, Anthropic, Gemini, Llama, Mistral, DeepSeek, or similar providers.
• Implement LLM evaluation, monitoring, tracing, and observability using LangSmith and Langfuse.
• Optimize prompts, retrieval strategies, latency, and inference performance.
• Deploy and manage AI services using Docker, Docker Compose, and Linux servers.
• Collaborate with product and engineering teams to deliver reliable AI-powered features.

• LangChain or LlamaIndex
• Fine-tuning using Hugging Face, LoRA, QLoRA, PEFT, or SFT
• Experience with vLLM, Ollama, or other model-serving frameworks
• Kubernetes, Nginx, CI/CD, GitHub Actions
• Cloud platforms such as AWS, Azure, or GCP
• Multi-agent systems, MCP (Model Context Protocol), and AI orchestration frameworks

• 3+ years of Python/backend development experience.
• Proven experience building and deploying AI applications used in production.
• Strong problem-solving skills and ability to own features end-to-end.
• Passion for modern Generative AI technologies and continuous learning.

If you’ve built real-world AI systems, production RAG pipelines, AI agents, and know how to evaluate, deploy, and scale LLM applications, we’d love to connect with you.

🚀 Immediate Joiners will be given preference.