Senior FDE (AI & Backend)

Pragyaa; Gurugram District; Vor Ort; INR 3.500.000 - 6.000.000; Vollzeit

Zusammenfassung

Pragyaa seeks a Senior SDE to own the architecture and build critical backend services on a Django/DRF stack. You will define service boundaries, data models, and MCP integration, then implement reliable pipelines and scalable async flows.

You will mentor juniors, conduct design reviews, and ensure architectures scale safely while balancing cost and performance in an AI-enabled platform.

Qualifikationen

• Designed and evolved non-trivial production systems with service boundaries and data modeling.
• Defends trade-offs in design reviews focusing on reliability, latency, and cost.
• Has production backend experience: Python with Django/DRF and PostgreSQL.

Aufgaben

• Own platform architecture and service design across data models and integrations.
• Write design docs and ADRs; build critical paths and reliable backend services.
• Mentor juniors; drive architectural reviews and guardrails for multi-agent flows.

Kenntnisse

System design

Scalability

Security

Backend architecture

Leadership & mentoring

Python/Django/DRF

PostgreSQL

Azure/CI-CD

Tools

Django/DRF

PostgreSQL

Azure

Redis/Celery

Jobbeschreibung

We are building AI-native products on the Anthropic API and MCP, backed by a Django/DRF + PostgreSQL platform with Celery/Redis pipelines and a React/Next.js frontend, deployed on Azure. The team works in an AI-assisted workflow (agentic AI coding tools are a daily tool), and the codebase is young: designs are still being set, and agent patterns, evals and observability are not yetstandardised. This is an architect-and-build seat, not a keep-the-lights-on role. The Senior SDE is the technical authority on system design: they decide how services are cut, how data flows, how agents and connectors plug in, and how the system scales and fails safely. They set thebarthe Junior SDEs work to.

What the role owns

Own the architecture and the services built on it:designthe overall system (service boundaries, data model, integration and agent architecture, MCP tool surface), write the design docs and ADRs, thenbuildthe critical paths yourself,buildreliable Django/DRF services and async pipelines,decidetrade-offs on cost, latency and reliability,reviewcode and designs, andmentorjuniors so repeat issues drop.

The actual workload (by share of time)

• e.g. "Design the platform for 10x document volume"
• e.g. "Monolith vs services for the agent runtime"
• e.g. "Write the ADR for the queue and storage choices"

Agent, skills & MCP connector architecture (~25%)

Custom agents/subagents, orchestration, skill design, connector and tool design, guardrails, context/memory

• e.g. "Design the multi-agent flow for document review"
• e.g. "Build the connector for the client's DMS"
• e.g. "Turn this SOP into a reusable skill"

Backend delivery (~15%)

Django/DRF, PostgreSQL models and performance, JWT/OAuth2, permissions on the critical paths

• e.g. "Redesign the data model for workflows"
• e.g. "Index and query plan for the cases list"

Async pipelines & reliability (~15%)

• e.g. "LLM calls time out and double-process"
• e.g. "Add regression evals and cost tracking"
• e.g. "Review a junior's agent PR"
• e.g. "Write the AI-assisted-code review checklist"

DevOps, incidents & stakeholder scoping (~10%)

Docker/Azure/CI-CD, RCA, turning business asks into tickets

• e.g. "Break this client ask into scoped tickets"

Priority reality:

stakeholders will call everything urgent and everything an AI problem. The Senior SDE re-triages againstreal businessimpact, pushes back when a problem needs no LLM, and escalates only with a diagnosis and a recommendation.

• AI/LLM engineering:Anthropic API, MCP (Model Context Protocol), agentic AI coding tools (CLI/IDE), reusable agent skills (SKILL.md-style), custom agents/subagents, custom MCP connector creation, LLM agent architecture & orchestration, prompt engineering, multi-agent systems, AI workflow automation. Optional: OpenAI API, RAG pipelines.
• Architecture &system design:service/data architecture, API design, event-driven and async patterns, scalability, multi-tenancy, design docs/ADRs, observability.
• Testing & Quality (optional):pytest, TDD.
• Frontend:React/Next.js, TypeScript, REST API integration.

Preferred qualifications

Must-have

• System design & architecture:has designed and evolved a non-trivial production system — service boundaries, data modelling, API design, caching, queues,consistencyand failure modes — and can defend trade-offs in a design review.
• Scalability & reliability:capacity planning, horizontal scaling, DB performance (indexing, query plans, partitioning), retries/idempotency, graceful degradation, SLOs.
• Security & multi-tenant design:authN/authZmodels, tenant isolation, secrets, audit logging, least-privilege access for agents and connectors.
• Production backend:4+ years in Python, with 2+ years on Django/DRF and PostgreSQL.
• Shipped LLM features:at least one in production on the Anthropic API — tool use, prompt iteration, failure handling.
• Agent skills & custom agents:authored production skills (SKILL.md, references, scripts, evals) and configured custom agents/subagents with scoped tools and permissions.
• Agent architecture:orchestration, multi-agent coordination, context/memory management, guardrails.
• Auth &security:JWT/OAuth2, permissions,secretshandling.
• Designcommunication:writes clear design docs/ADRs, runs design reviews and presents architecture to technical and non-technical stakeholders.
• Delivery:Docker + CI/CD on Azure (or equivalent) with ownership of a live deployment.
• Leadership:code review, design-doc writing and mentoring record; clear written comms with non-technical stakeholders.

Strongly preferred

• Agentic AI coding toolsin daily use, with a point of view on where AI-generated code needs extra review.
• Event-driven & integration architecture:message queues/streams, webhooks, API gateways, versioned APIs, backward-compatible migrations.
• Cloud architecture on Azure:networking, managed Postgres/Redis, containers/orchestration, cost-aware design,infrastructure ascode.
• Team enablement:has set conventions for skills, agentdefinitionsand connector reviews so others can reuse them.
• Evals & observability for LLM systems— regression sets,costand latency tracking.
• Business-workflowautomation:turned messy real workflows into reliable agent flows.
• React/Next.js + TypeScriptenough to review and unblock frontend work.

Nice-to-have:

OpenAI API and cross-model fallbacks; RAG pipelines (embeddings,pgvector, retrieval evals);pytestand TDD leadership; Sentry; AWS; PostgreSQL performance tuning; domain-driven design; distributed tracing (OpenTelemetry); Kubernetes; Terraform/Bicep.

This isfirstand foremostan architectureand AI-systemsownership hire. Weight evaluation toward system-design judgement (a design round),productionLLM experience and the ability to raise the team's level — nota long listof tools.