Software Platform Engineer II

MetLife, Inc.; Pune District; Híbrido; INR 900.000 - 1.800.000; Jornada completa

Descripción de la vacante

Metlife in Pune is seeking a software engineer to design and implement production APIs and microservices in Python using FastAPI and async I/O. The role focuses on building agentic AI workflows, deploying models, and optimizing latency and cost across frontier AI platforms.

You will containerize services with Docker, manage Helm manifests, and debug Kubernetes (AKS) workloads, while partnering with frontend teams (React/Next.js/TypeScript) to deliver end-to-end AI features and robust CI/CD and

Formación

• Design and implement production APIs and microservices in Python (FastAPI, async I/O).
• Build agentic AI workflows and orchestration with LangGraph/LangChain for tool calling, multi-step orchestration, context & memory management, retries, and guardrails.
• Ship and operate production agents on frontier models; optimize for latency, cost, and reliability.
• Package, serve, version, and optimize ML/LLM models for low-latency and batch/async inference (MLflow/LangSmith or equivalent).
• Implement LLM features: embeddings, retrieval-augmented generation (RAG), vector search, and prompt & context engineering.
• Build resilient event-driven integrations (Event Hubs/Kafka patterns), idempotent consumers, and backfill/replay strategies.
• Containerize services (Docker), author manifests/Helm charts, and debug Kubernetes (AKS) workloads.
• Instrument services and models (logging, metrics, tracing), define SLOs, and lead incident triage and remediation.
• Deliver automated tests and CI/CD for services and model pipelines; collaborate on release gating and security scans.
• Partner with frontend (React/Next.js/TypeScript) to deliver end-to-end AI features.

Responsabilidades

• Design and implement production APIs and microservices in Python (FastAPI, async I/O).
• Build agentic AI workflows and orchestration with LangGraph/LangChain for tool calling, multi-step orchestration, context & memory management, retries, and guardrails.
• Ship and operate production agents on frontier models; optimize for latency, cost, and reliability.
• Package, serve, version, and optimize ML/LLM models for low-latency and batch/async inference (MLflow/LangSmith or equivalent).
• Implement LLM features: embeddings, retrieval-augmented generation (RAG), vector search, and prompt & context engineering.
• Build resilient event-driven integrations (Event Hubs/Kafka patterns), idempotent consumers, and backfill/replay strategies.
• Containerize services (Docker), author manifests/Helm charts, and debug Kubernetes (AKS) workloads.
• Instrument services and models (logging, metrics, tracing), define SLOs, and lead incident triage and remediation.
• Deliver automated tests and CI/CD for services and model pipelines; collaborate on release gating and security scans.
• Partner with frontend (React/Next.js/TypeScript) to deliver end-to-end AI features.

Conocimientos

Python

FastAPI

LangChain

AI workflows

Git CI/CD

Logging/Monitoring

Kubernetes

Docker

Frontend collaboration

Herramientas

Docker

Kubernetes

Helm

AKS

MLflow

LangSmith

LangGraph

LangChain

React

Next.js

TypeScript

Descripción del empleo

Job Summary

Location: Pune

Working Schedule: Full-Time

Work Arrangement: Hybrid

Description and Requirements

• Design and implement production APIs and microservices in Python (FastAPI, async I/O).
• Build agentic AI workflows and the surrounding harness with LangGraph/LangChain - tool calling, multi-step orchestration, context & memory management, retries, and guardrails.
• Ship and operate production agents on frontier models (Claude, GPT, Gemini); optimize for latency, cost, and reliability.
• Package, serve, version, and optimize ML/LLM models for low-latency and batch/async inference (MLflow/LangSmith or equivalent).
• Implement LLM features: embeddings, retrieval-augmented generation (RAG), vector search, and prompt & context engineering.
• Build resilient event-driven integrations (Event Hubs/Kafka patterns), idempotent consumers, and backfill/replay strategies.
• Containerize services (Docker), author manifests/Helm charts, and debug Kubernetes (AKS) workloads.
• Instrument services and models (logging, metrics, tracing), define SLOs, and lead incident triage and remediation.
• Deliver automated tests and CI/CD for services and model pipelines; collaborate on release gating and security scans.
• Partner with frontend (React/Next.js/TypeScript) to deliver end-to-end AI features.