Software Platform Engineer II

MetLif; Pune District; On-site; INR 2,500,000 - 5,000,000; Full time

Job summary

MetLife is seeking a skilled AI/ML backend engineer in Pune to design production APIs, build agentic AI workflows, and optimize frontier-model deployments. You will containerize services, implement RAG and vector search, and collaborate with front-end teams to deliver end-to-end features.

The role emphasizes reliability, scalability, and security across ML pipelines, with CI/CD, incident triage, and performance tuning as core duties.

Qualifications

• Experience building production-grade AI workflows and APIs.
• Strong Python expertise with async patterns and FastAPI.
• Familiarity with LLM tooling and orchestration frameworks.

Responsibilities

• Design and implement production APIs and microservices in Python (FastAPI, async I/O).
• Build AI workflows with LangGraph/LangChain, including tool calling and orchestration.
• Operate production agents on frontier models with latency and cost optimization.
• Package and serve ML/LLM models for low-latency inference and batching.
• Implement embeddings, RAG, vector search, and prompt/context engineering.
• Build event-driven integrations with Kafka/Event Hubs; ensure idempotence.
• Containerize services with Docker and manage Kubernetes/AKS deployments.
• Instrument services with logging/metrics/tracing; define SLOs and triage incidents.
• Deliver automated tests and CI/CD; support release gating and security scans.
• Collaborate with frontend teams (React/Next.js/TypeScript) for end-to-end features.

Skills

Python

FastAPI

Async I/O

LangGraph

LangChain

Tool calling

Orchestration

Memory management

Retries

Guardrails

LLM models

Embeddings

RAG

Vector search

Prompt engineering

Event Hubs

Kafka

Docker

Kubernetes

AKS

SLOs

Incident triage

CI/CD

Security scans

React

Next.js

TypeScript

Tools

Docker

Kubernetes

AKS

MLflow

LangSmith

LangGraph

React

Next.js

TypeScript

Job description

• 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.

About MetLife

Recognized on Fortune magazine's list of the "World's Most Admired Companies" and Fortune World’s 25 Best Workplaces™, MetLife, through its subsidiaries and affiliates, is one of the world’s leading financial services companies; providing insurance, annuities, employee benefits and asset management to individual and institutional customers. With operations in more than 40 markets, we hold leading positions in the United States, Latin America, Asia, Europe, and the Middle East. As part of our New Frontier strategy, MetLife is building an AI-enabled, people-centered future. We’re looking for people who bring curiosity, adaptability, and a growth mindset as we use AI to enhance how we serve customers, support communities, and evolve the way work gets done. At MetLife, AI is a responsible partner that supports human judgment, creativity, and continuous improvement while helping us build trust, inclusion, and long-term value. Our purpose is simple - to help our colleagues, customers, communities, and the world at large create a more confident future. United by purpose and guided by our core values - Win Together, Do the Right Thing, Deliver Impact Over Activity, and Think Ahead - we’re inspired to transform the next century in financial services. At MetLife, it’s #AllTogetherPossible .