AI Backend Engineer (Agentic)

We are looking for an AI Engineer who has hands-on experience in agentic AI, RAG pipelines, LLM orchestration, and scalable backend systems to help build next-generation AI products.

Responsibilities:

• Design and build Agentic AI applications using LLMs, tools, and autonomous workflows.
• Develop and optimize RAG (Retrieval Augmented Generation) pipelines for enterprise-scale knowledge retrieval.
• Integrate vector databases, document ingestion systems, and observability frameworks.
• Work on prompt engineering, context management, evaluation, and model optimization.
• Build AI-powered products leveraging OpenAI/Anthropic/Gemini and open-source LLMs.
• Collaborate with product, engineering, and data teams to deliver production-ready AI solutions.
• Drive improvements in latency, accuracy, scalability, and AI infrastructure costs.

Requirements:

• Engineers who have shipped AI features/products to production.
• Strong problem-solving and system design skills.
• Ability to work in a fast-paced product environment.
• Passion for building innovative AI-first experiences.
• 3-7 years of software engineering experience.
• Strong proficiency in Python and/or Golang.
• Hands-on experience with agentic AI frameworks, LangChain / LangGraph, RAG architecture, prompt engineering, LLM evaluation and optimization, vector databases (Pinecone, Weaviate, Chroma, etc. ), OpenAI, Anthropic, Gemini APIs, document processing, and knowledge retrieval.
• Experience with PostgreSQL / NoSQL databases, REST APIs and microservices, cloud platforms (AWS / GCP / Azure), Docker, and Kubernetes.
• Preferred Skills: AI observability tools (Langfuse, LangSmith, Helicone), multi-agent systems, fine-tuning and model customization, MCP (Model Context Protocol), and AI workflow automation.
• Experience building enterprise AI products from scratch.