Senior AI Engineer

Recro; Bengaluru; On-site; INR 2,800,000 - 4,000,000; Full time

Job summary

Recro in Bengaluru is seeking a Senior AI Engineer (5–7 years) to drive system architecture and execution within lean AI pods, building scalable backend infrastructure and complex agent topologies.

You will lead design discussions, own production deployments in a 2-person pod, and ensure rigorous engineering standards across the delivery lifecycle, with deep expertise in Python, FastAPI, Docker, and AWS EKS/Kubernetes.

Qualifications

• 5–7 years in backend production engineering.
• 2–3+ years shipping multi-tool agentic applications.
• Deep knowledge of Python, FastAPI, microservices, Docker, AWS EKS/Kubernetes, and CI/CD.
• Ability to explain end-to-end architectures of real-world systems built, deployed, and monitored.
• Domain depth in agent execution loops, state management, ground-truth evaluations, and observability tools.

Responsibilities

• Design system architecture with high-throughput Python services using FastAPI, containers, and EKS/Kubernetes.
• Architect complex agent loops, state persistence, tool integration, and multi-agent interactions.
• Establish evaluation frameworks, ground-truth datasets, logging pipelines, and observability stacks.
• Evaluate framework implementations and document decisions and trade-offs.
• Drive product delivery in a 2-person pod, owning RFC/design to production.

Skills

Backend engineering

Agentic AI

Python

FastAPI

Microservices

CI/CD

Observability

Tools

Docker

Kubernetes / AWS EKS

FastAPI

Job description

We are seeking a Senior AI Engineer (5–7 years experience) to drive system architecture and execution within our lean AI engineering pods. You will build resilient, scalable backend infrastructure and construct complex agent topologies. You are expected to operate with high independence, lead technical design discussions, and maintain rigorous engineering standards across the entire delivery lifecycle.

Key Responsibilities

• System Architecture: Design and develop high-throughput, fault-tolerant Python services utilizing FastAPI, containerization, and EKS/Kubernetes orchestration.
• Advanced Agentic Engineering: Architect complex agent loops, state persistence strategies, tool integration layers, and multi-agent interaction systems.
• Evals & Observability Infrastructure: Establish robust evaluation frameworks, ground-truth benchmark datasets, logging pipelines, and real-time observability stacks.
• Trade-Off Analysis: Evaluate framework implementations (LangGraph, LangChain, Strands, ADK vs. custom components), documenting technical decisions and performance trade-offs.
• Independent Execution: Drive product delivery in a 2-person pod model without relying on large support teams, taking ownership from RFC/design to production deployment.

Required Qualifications & Experience

• Experience: 5–7 years in backend production engineering and systems development.
• Agentic AI Expertise: 2–3+ years of production experience shipping multi-tool agentic applications into production environments.
• Technical Mastery: Deep knowledge of Python, FastAPI, microservices architecture, Docker, AWS EKS/Kubernetes, and CI/CD pipelines.
• Hands-on Production Track Record: Ability to explain end-to-end architectures of real-world systems you personally built, deployed, and monitored in production.
• Domain Depth: Complete grasp of agent execution loops, state management, ground-truth evaluations, and system observability tools.