Backend Engineer (AI)

Responsibilities:

• Design, develop, and deploy production-grade AI-powered backend systems for enterprise applications.
• Build and own agentic AI workflows, autonomous agents, multi-agent orchestration, and tool-calling pipelines.
• Develop and integrate solutions using modern LLM platforms OpenAI, Anthropic, Gemini, or similar.
• Build scalable RAG pipelines for intelligent document processing and contextual retrieval.
• Develop robust backend services and REST APIs using Python to support AI inference and enterprise workflows.
• Work with large-scale structured and unstructured datasets to generate actionable insights.
• Develop and optimize ML models and AI workflows for production environments.
• Contribute to MLOps practices: model deployment, monitoring, and lifecycle management.
• Work closely with Palantir Foundry and enterprise data ecosystems to drive business outcomes.
• Collaborate directly with global clients and cross-functional teams to translate business requirements into scalable AI solutions.

Requirements:

• 4-8 years of experience in AI engineering, backend development, or ML engineering.
• Strong hands-on Python (Mandatory).
• Agentic AI experience (mandatory): hands-on building and deploying autonomous AI agents in production.
• Experience with agentic frameworks LangGraph, LangChain, LlamaIndex, CrewAI, or AutoGen.
• Deep understanding of RAG architectures, vector DBs, embeddings, and document pipelines.
• Experience with LLM APIs like OpenAI, Anthropic, or similar.
• Hands-on with vector databases Pinecone, Weaviate, Chroma, or pgvector.
• Strong understanding of ML model development and deployment.
• Experience with FastAPI or similar Python frameworks for building backend services.
• Strong communication skills, comfortable working directly with enterprise clients and global stakeholders.
• Comfortable working in a 4:00 PM - 1:00 AM IST shift to align with US business hours.

Good to Have:

• Hands-on experience with Palantir Foundry (highly preferred).
• Experience with Databricks, Snowflake, or similar data platforms.
• Exposure to MLOps, LLMOps, and production monitoring frameworks.
• Cloud platform experience in AWS, Azure, or GCP.
• Background in data engineering or distributed systems.
• Experience in client-facing or forward-deployed engineering roles.
• Familiarity with Docker, Kubernetes, or CI/CD pipelines.