Senior Software Engineer - AI & Cloud [Bengaluru]

Labra

Bengaluru, Bengaluru Urban

Remote

INR 4,200,000 - 6,800,000

Full time

14 days+

Get a reply from this employer

Your resume and cover letter, tailored to exactly what they’re hiring for.

Get past ATS filters

Job summary

Labra in Bengaluru, India (In-office) is seeking a Senior Software Engineer specializing in Cloud & AI to build AI agents, the sync engine, and full-stack features that power enterprise integrations.

You'll own end‑to‑end delivery, design scalable systems, mentor teammates in your pod, and ship production-ready code with a focus on performance, reliability, and cost efficiency across AWS, GCP, and modern tooling.

Qualifications

  • 5+ years of production software experience
  • Proficient in Python, Go, or TypeScript; primarily Python
  • Experience with React/TypeScript frontends
  • Strong knowledge of AWS, GCP, or Azure in production

Responsibilities

  • Own AI/LLM features and integration across three areas.
  • Design, implement, review code, and mentor engineers.
  • Ensure production readiness with tests, metrics, and alerts.
  • Collaborate in a fast-paced startup environment.

Skills

Mentoring junior engineers
Python
Go
TypeScript/React
AWS
LLMs / AI agents
REST API design
Distributed systems
Debug production issues

Tools

FastAPI
Flask
NestJS
PostgreSQL
MongoDB
OpenSearch
AWS SQS/SNS/Lambda
Docker
Terraform

Job description

Senior Software Engineer (Cloud & AI)

Cloud & amp; AI | Labra | Bengaluru (In-office)

Build the AI agents, sync engine, and full-stack product that keep enterprise CRMs and cloud partner programs in lockstep, and own them in production.

Title : Senior Software Engineer (Cloud & AI)

Experience: 5+ years of professional software engineering

Core stack: Python, TypeScript/React, AWS, GCP, Azure, LLMs

Location: Bengaluru, India (In-office)

Employment type: Full-time

About Labra

Labra builds cloud-native B2B SaaS products powered by AI agents that help companies accelerate their cloud transformation. Our teams work at the intersection of generative AI, AI agents, cloud infrastructure, and modern full-stack engineering, shipping products that customers and internal teams use every day.

The Role

This is a hands‑on role with real scope across three areas: AI agents and LLM features, the backend and sync engine, and the React product customers use. Your depth can be in one area, as long as you're comfortable working across all three.
You'll join a pod that pairs feature work with stability work. You'll take problems from a half‑formed customer need to a feature running reliably in production: designing the system, writing most of the code, reviewing teammates' work, and being accountable for how it behaves once it ships.

What You'll Own
AI agents and LLM features
  • Build production AI agents and LLM features with RAG, tool calling, and MCP-based workflows.
  • Design context management: memory, compression, retrieval, and prompt optimization.
  • Optimize time to first token (TTFT), latency, token usage, and cost through caching, parallel tool execution, and fewer unnecessary LLM calls.
  • Ship streaming AI experiences over SSE and WebSockets.
Sync engine and integrations
  • Design, build, and ship integrations with business systems such as CRMs and ERPs, including sync configuration and co‑sell pipeline visibility.
  • Make high‑volume, bidirectional sync between CRMs and cloud partner programs fast, correct, and recoverable.
  • Build event‑driven processing on AWS SQS, EventBridge, SNS, Lambda, and Step Functions, with robust retries, idempotency, and dead‑letter handling.
Full‑stack product
  • Build customer‑facing features in React and TypeScript, backed by well‑designed REST APIs and services in Python or Go.
  • Implement authentication, authorization, RBAC, and secure third‑party integrations.
  • Profile slow endpoints and queries, tune connection pools and aggregation pipelines, and load‑test before customers hit the limits.
  • Write automation and unit tests for your code before it is deployed.
Production and engineering quality
  • Add the metrics, logs, traces, and alerts that catch issues first, and cut alert noise so real signals stand out.
  • Join the on‑call rotation, lead incident debugging, and ship root‑cause fixes rather than patches.
  • Improve scalability, reliability, and cloud cost efficiency on AWS.
  • Write design docs, review code, raise test coverage, and mentor junior engineers in your POD.
Our Stack

Languages: Python (primary), TypeScript, Go

Frontend: React, TypeScript

Backend frameworks: FastAPI, Flask, NestJS

AI and LLMs: Amazon Bedrock, AgentCore, Claude, MCP, LangChain / LangGraph

Data and search: PostgreSQL (RDS), MongoDB / DocumentDB, DynamoDB, OpenSearch

Async and messaging: AWS SQS, SNS, Lambda, Step Functions, EventBridge

Cloud and infra: AWS (ECS Fargate, IAM, S3), GCP (Cloud Run), Azure, Docker, Terraform, CloudFormation, Jenkins

Integrations: Salesforce APIs (incl. Bulk API, Canvas), HubSpot, AWS ACE, Workato
AI development tools: Cursor, Copilot, Claude Code

What You Bring
  • Proven track record of mentoring and developing junior team members (very important).
  • 5+ years building and running software in production, ideally in a B2B SaaS product.
  • Strong in Python, Go, or TypeScript, and willing to work mainly in Python.
  • Hands‑on experience with React and TypeScript for production frontends.
  • Solid REST API design and experience with microservices, distributed systems, and asynchronous processing, ideally on AWS SQS, SNS, and Lambda: queues, retries, idempotency, and failure handling.
  • Depth in at least one relational database (PostgreSQL or MySQL) and one NoSQL store (MongoDB or DynamoDB): schema design, indexing, and query tuning.
  • Experience building or integrating LLM features, AI agents, RAG, or tool‑calling systems, with a working grasp of context windows, token management, and retrieval.
  • Understanding of TTFT, streaming, latency optimization, and caching.
  • Hands‑on AWS (and Azure or GCP) production deployments, plus Docker, Git, CI/CD, and automated testing.
  • Comfort debugging production issues from logs, metrics, and traces.
  • A track record of owning a feature or service from design through production support.
  • Clear written communication: design docs, tickets, and updates people can act on.
Nice to Have
  • Hands‑on work with MCP servers or clients, Amazon Bedrock, or Bedrock AgentCore.
  • Agent orchestration with LangChain or LangGraph, and LLM evaluation, guardrails, or agent observability.
  • Workflow orchestration with Temporal, Airflow, Step Functions, or Celery.
  • CRM integration experience, especially Salesforce or HubSpot APIs.
  • OpenSearch or other vector and search engines for retrieval.
  • Infrastructure as code with Terraform or CloudFormation.
  • Load testing (k6, Locust) and observability tooling.
  • Familiarity with cloud partner programs or marketplaces (AWS ACE, Azure, GCP).
How We Work
  • We're a fast-paced startup where a small team ships to large enterprises, and priorities shift with customer needs. You'll thrive here if you:
  • Act like an owner. Your service's uptime, performance, and customer impact are yours, not someone else's ticket.
  • Close the loop. Merged isn't done. You confirm it works in production and follow up until the customer's problem is solved.
  • Move fast without breaking trust. You ship in small, safe increments and know when a shortcut will cost us later.
  • Handle ambiguity. Given a half‑formed problem, you ask sharp questions, propose a plan, and get moving.
  • Raise problems early. You flag risks, slips, and bad ideas, including your own, before they become surprises.
  • Keep learning. You try new AI, agent, and cloud tools and bring back what works.
  • Lift the team. You review carefully, share context in writing, and help newer engineers level up.
What You Get
  • AI in production, not prototypes. Ship agents, RAG, and LLM features that enterprise customers use every day.
  • Hard performance problems. Work on TTFT, streaming, token cost, and high‑volume sync at enterprise scale.
  • Real ownership. Own high‑impact systems that customer revenue depends on, from design through on‑call.
  • Direct customer exposure. Work on enterprise customers' actual problems, not just tickets about them.
  • Room to grow. Shape our platform's architecture and follow a clear path toward pod lead or tech lead.
Get your free, confidential resume review.

or drag and drop your file here.

Similar jobs

Similar jobs worth comparing

Senior AI Engineer
Senior AI Engineer

Blaugarnet Inc. • Pune District

Hybrid
INR 3,000,000 - 5,000,000
Associate AI Engineer
Associate AI Engineer

MVP1 Ventures • India

Remote
INR 1,500,000 - 3,200,000
AI Product Engineer
AI Product Engineer

PingAura AI • Mumbai

Remote
INR 900,000 - 1,300,000
Software & AI Engineer
Software & AI Engineer

HealthMinds Consulting • Bengaluru

On-site
INR 1,800,000 - 2,600,000
AI Engineer
AI Engineer

OnIT India • Pune District

On-site
INR 1,500,000 - 2,500,000
Applied AI Engineer
Applied AI Engineer

PingAura AI • Mumbai

On-site
INR 3,000,000 - 6,000,000
Full Stack Engineer
Full Stack Engineer

Enterprise Bot • Bengaluru

On-site
INR 1,200,000 - 2,000,000
Competitive compensation
Global engineering team
High ownership
+1
Senior Backend Developer
Senior Backend Developer

JobItUs • Kolkata District

On-site
INR 2,000,000 - 4,200,000
Tech Principal, AI Solutions
Tech Principal, AI Solutions

Newpage Solutions • India

Hybrid
INR 4,000,000 - 7,000,000
People-first culture
Career development opportunities
Flexible work arrangements
+1
AI Engineer
AI Engineer

AlgoLeap Technologies Pvt Ltd. • Hyderabad

On-site
INR 1,800,000 - 2,400,000