Overview
We’re looking for a hands-on backend expert who can take our FastAPI-based platform to the
next level: production-grade model-inference services, agentic AI workflows, and seamless
integration with third-party LLMs and NLP tooling.
WHAT YOU'LL BUILD
1. Core Backend Enhancements
- Build APIs
- Harden security (OAuth2/JWT, rate-limiting, SecretManager) and observability (structured logging, tracing)
- Add CI/CD, test automation, ,health checks and SLO dashboards
2. Awesome UI Interfaces
- React.js/Next.js, Redact/Context, Tailwind / MUI / Custom-CSS / Shadcn / Axios
3. LLM & Agentic Services
- Design micro/mini-services that host and route to OpenAI, Anthropic, local HF models, embeddings & RAG pipelines
- Implement autonomous/recursive agents that orchestrate multi-step chains (Tools, Memory, Planning)
4. Model-Inference Infrastructure
- Spin up GPU / CPU inference servers behind an API gateway
- Optimize throughput with batching, streaming, quantization & caching (Redis / pgvector)
5. NLP & Data Services
- Own the NLP stack: Transformers for classification, extraction, and embedding generation.
- Build data pipelines that join aggregated business metrics with model telemetry for analytics
TECH STACK YOU'LL WORK WITH
1.Fullstack/Backend Infrastructure
• Python, FastAPI, Starlette, Pydantic
• Async SQLAlchemy, Postgres, Alembic, pgvector
• Docker, Kubernetes, or ECS/Fargate - AWS (Or) GCP
• Redis / RabbitMQ / Celery (jobs & caching)
• Prometheus, Grafana, OpenTelemetry
• If you are a full-stack person, then - react.js / next.js / shadcn / tailwind.css / MUI
2.AI / NLP
• HuggingFace Transformers, LangChain / Llama-Index, Torch / TensorRT
• OpenAI, Anthropic, Azure OpenAI, Cohere APIs
• Vector search (Pinecone, Qdrant, PGVector)
3. Tooling
• Pytest, GitHub Actions
• Terraform / CDK preferred
MUST HAVE EXPERIENCE
• 3+ yrs building production Python REST APIs (FastAPI, Flask, or Django-REST)
• SQL schema design & query optimization in Postgres (CTEs, JSONB)
• Deep knowledge of async patterns & concurrency (asyncio, AnyIO, celery)
• Crafted awesome UI Applications that integrate with the backend API
• Hands-on with RAG, LLM/embedding workflows, prompt-engineering & at least one of “agent-ops” frameworks (LangGraph, CrewAI, AutoGen)
• Cloud container orchestration (Any of K8s, ECS, GKE, AKS, etc.)
• CI/CD pipelines and infra-as-code
NICE-TO-HAVE EXPERIENCE
• Streaming protocols (Server-Sent Events, WebSockets, gRPC)
• NGINX Ingress / AWS API Gateway
• RBAC / multi-tenant SaaS security hardening
• Data privacy, PII redaction, secure key vault integrations
• Bitemporal or event-sourced data models
WHY DOES THIS ROLE MATTER?
We’re growing fast. Products are live, but evolving. Challenges are real, and the opportunity to own systems end-to-end is massive. You’ll lead how we scale AI services, work directly with the founder, and shape what the next wave of our platform looks like.
If you’re looking for meaningful ownership and a chance to work on hard, forward-looking problems, this role is for you.
