About the role
Helpware is building a multi-tenant B2B AI platform for customer support operations — a product portfolio spanning Agent Assist, AI-powered QA, document processing, support automation, workforce management, and others.
We’re looking for a Sr. Full Stack Developer to build product features end-to-end — services that orchestrate LLM workflows on AWS, and the frontends that put those capabilities in front of support teams and their supervisors. You’ll work in a codebase governed by explicit engineering standards, so this role suits someone who values engineering discipline as much as shipping.
What you’ll do
Build new features assited by Claude Code and relying on AI Spec Driven Design Development.
Design and build backend services in Python (FastAPI) on a multi-tenant PostgreSQL data model, including async and batch workloads (AWS Lambda, Batch, ECS).
Integrate LLM capabilities into product features, primarily using Amazon Bedrock and agentic workflows, following the platform’s prompt management and evaluation conventions.
Build responsive, accessible web frontends (React / TypeScript) for supervisor dashboards, review queues, and configuration surfaces.
Implement integrations with customer helpdesks and third-party systems (webhooks, REST APIs, MCPs).
Instrument everything you ship per the platform’s architectural standards.
Write tests, participate in code review, and contribute to ADRs when your work touches architectural decisions.
Work with product and QA to turn accuracy and latency targets into shipped, measured features.
What we’re looking for
5+ years building production web applications across backend and frontend.
Strong Python; production experience with FastAPI or a comparable async framework.
Experience with Claude Code and AI Spec Driven Design
Solid relational database skills (PostgreSQL preferred), including experience with multi-tenant data models or a clear grasp of tenant isolation patterns.
Proficiency in a modern frontend framework (React preferred) with TypeScript.
Experience consuming or building LLM-powered features: prompt design basics, streaming responses, handling latency/cost/failure modes of model APIs.
Comfort with AWS fundamentals (ECS/Lambda, S3, RDS, IAM basics) — you don’t own the infrastructure, but you deploy to it and debug in it.
Habit of working within standards: structured logging, tracing, contract tests, linters — and improving them rather than routing around them.
Nice to have
Hands-on experience with Amazon Bedrock, Bedrock Guardrails, or LLM gateways (e.g., LiteLLM).
Familiarity with LLM observability tooling (Langfuse, OTel GenAI semantic conventions) or agent frameworks (CrewAI, LangGraph).
Experience in customer support / contact center / BPO tech, or with helpdesk APIs (Zendesk, Freshdesk, Intercom, etc.).
Exposure to PII handling, data governance, or compliance-sensitive domains (SOC 2, HIPAA, GDPR).
