Scope

Job description

Employ is hiring a Senior AI Engineer for a full-time, hybrid role in Bangalore, India. The position sits within the AI Foundations team and focuses on defining and building production-grade AI systems that turn probabilistic model outputs into reliable product capabilities. The engineer will lead architecture across agents, retrieval pipelines, orchestration layers, evaluation frameworks, APIs, state management, guardrails, observability, and scalable AI services.

Responsibilities

• Lead architecture and delivery of end-to-end AI-powered systems, including agents, RAG pipelines, orchestration layers, and reasoning workflows.
• Translate product vision into scalable technical systems.
• Define contracts, state-management strategies, and guardrails for AI-driven workflows.
• Own and evolve API contracts used by AI systems with reliability, idempotency, authentication safety, and rate limiting in mind.
• Design schema-enforcement and validation layers for AI-generated outputs.
• Implement retries, fallback strategies, and failure-mode containment.
• Establish evaluation frameworks for benchmarking, regression testing, and drift detection.
• Define observability standards including structured logging, telemetry, tracing, and performance monitoring.
• Productionize experimental AI capabilities into scalable and secure services.
• Establish architectural patterns and standards that can be adopted across engineering teams.
• Mentor engineers in AI-native and spec-driven development practices.
• Break high-level business outcomes into executable technical systems.

Requirements

• 4+ years building AI-augmented product capabilities involving LLMs, RAG systems, agents, or orchestration frameworks.
• Strong Python expertise, including asyncio, decorators, and the modern Python ecosystem.
• TypeScript / Node experience for integration and application-layer logic.
• Experience designing event-driven and asynchronous systems using queues such as Kafka, SQS, or BullMQ.
• Experience persisting state across sessions, managing context windows, and handling concurrency and race conditions in multi-agent systems.
• Experience enforcing structured outputs with tools such as Pydantic, Zod, or JSON Schema.
• Strong API design and integration knowledge across REST, GraphQL, or RPC, including authentication, rate limiting, and idempotency.
• Hands-on experience with LangChain, LangGraph, custom agent loops, or similar orchestration frameworks.
• Experience with RAG, hybrid search, re-ranking, chunking strategies, and vector databases.
• Advanced SQL skills, including query optimization and indexing strategies.
• Experience with Docker, Kubernetes, or similar container/orchestration platforms.
• Ability to turn AI experiments into reliable, scalable, secure production services.

Skills

• Artificial Intelligence
• Generative AI
• LLMs
• AI Agents
• RAG
• LangChain
• LangGraph
• Python
• TypeScript
• Node.js
• REST APIs
• GraphQL
• RPC
• Kafka
• Amazon SQS
• BullMQ
• Pydantic
• Zod
• JSON Schema
• Vector Databases
• Pinecone
• pgvector
• Weaviate
• SQL
• Docker
• Kubernetes
• Observability
• Evaluation Frameworks
• Distributed Systems