What kind of freelance AI and backend work do you take?

I focus on production systems: agentic AI workflows, RAG and retrieval design, LLM orchestration and tool-calling, FastAPI and Python backends, microservices, async job queues, vector search, and integrations (Stripe, RunPod, model APIs). I also support Next.js frontends when the project needs a full-stack loop.

Where can I see your portfolio and experience?

See the main portfolio at mrdasdeveloper.github.io for timeline, stack, featured projects (including WinstaAI), and open-source templates.

Accepting remote freelance & contract work

Hire Agentic AI freelancer

Q: Do you work with international clients remotely?

Yes. I am based in Nepal and work remotely with teams worldwide. Communication is in English via email, WhatsApp, and your preferred chat or video tools.

Q: How do you price freelance projects?

Most work is scoped as fixed milestones or monthly retainers after a short discovery call. Pricing depends on complexity, latency requirements, compliance (e.g. healthcare), and whether GPU inference or multi-tenant SaaS patterns are involved. Contact me with your brief for a quote.

Q: Can you join an existing codebase?

Yes. I regularly extend existing FastAPI, Django, or Node services, add AI features behind feature flags, and document APIs and runbooks so your team can own the system long term.

I help startups and product teams ship production AI platforms: RAG that actually works in the wild, LLM orchestration with guardrails, async Python services, and clear handoff docs. Six-plus years building real systems — currently lead AI on WinstaAI.

Fixed milestones Monthly retainer Code review & rescue Nepal · UTC+5:45 · English

✉ Start a project ⬡ Full portfolio ⌥ GitHub

Why this page exists

Google-friendly landing for “hire AI freelancer”, “RAG contractor”, and “FastAPI remote developer” — with the same engineer behind the main portfolio

Many teams discover me through my portfolio, GitHub, or referrals. This page is a focused freelancer profile: what I deliver, how engagements run, and how to reach me fast. If you need agentic workflows, vector search, model routing, or a hardened Python backend, you get senior execution without agency overhead. For a dedicated agentic AI developer landing (multi-agent, tool use, orchestration SEO), use that page. For full stack engineer / senior full stack engineer positioning across UI, APIs, data, and LLM features, use that landing. For 24/7 business automation (schedules, webhooks, integrations), see business automation services.

For depth on architecture patterns, see the AI backend & microservices guide and the presentation linked from the homepage.

Freelance services — scope, summary, and WhatsApp

Each card includes a short summary of what you get. Use Chat on WhatsApp to open a thread with that service pre-filled — same stack and experience as my portfolio tech stack.

Discovery → roadmap

AI & RAG architecture sprint

Design-first engagement for retrieval quality: data sources, chunking, embeddings, reranking, evals, and safety before you commit engineering weeks.

Problem framing, data sources, evaluation plan
Chunking, embeddings, reranking, latency budget
Threat model: prompt injection, PII, access control
Written architecture + backlog for your team

Typical: focused 1–2 week sprint · quote after brief

RAG LangChain LlamaIndex Vector search

💬 Chat about this service

Build & integrate

FastAPI, Django & microservices

Production Python and Node backends: async APIs, workers, auth, multi-service boundaries — aligned with how WinstaAI and past SaaS backends were built.

REST / async APIs, Celery jobs, observability hooks
PostgreSQL, Redis, Mongo, vector stores as needed
JWT, OAuth, RBAC, WebSockets, GraphQL where fit
Docker-ready layout, OpenAPI, README, runbooks

Milestone delivery · greenfield modules or new services

FastAPI Django Node.js Microservices

💬 Chat about this service

Agents & orchestration

Agentic AI & multi-agent systems

Tool-calling agents, multi-model routing, admin and metering patterns for SaaS — the same class of work as production agentic platforms on my CV.

Agent workflows, planners, tool registries, guardrails
Multi-model routing, fallbacks, cost controls
Stripe, PayPal, RunPod, FAL.ai, OpenAI-style APIs
Pairs with Next.js / React frontends when you need UI

Phased milestones · optional retainer for iteration

Agents LLM APIs SaaS LangChain

💬 Chat about this service

End-to-end product

Full-stack development (React / Next.js)

MVPs and product lanes across dashboard, marketing surfaces, and API integration — TypeScript, Tailwind, SSR/SSG, wired to your Python or Node backend.

Next.js App Router, React, TypeScript, Tailwind
Auth flows (Auth0, Firebase, custom JWT) and RBAC-aware UI
Billing UX hooks to Stripe / PayPal where needed
SSR, SEO-sensitive pages, performance passes

Full-stack milestones or frontend-only augment

Next.js React TypeScript Stripe

💬 Chat about this service

Automation & integrations

Workflow automation & internal tools

Reliable background processing and glue between systems: queues, webhooks, notifications, and third-party APIs so ops and product move faster with less manual work.

Celery / async workers, schedules, retries, idempotency
Webhooks, Twilio, DeepL, payment and AI provider hooks
Admin tooling, imports/exports, reporting pipelines
GitHub Actions and release automation patterns

Automation slices or ongoing integration retainers

Celery Webhooks Twilio GitHub Actions

💬 Chat about this service

Generative & media AI

Generative AI APIs — speech, vision, images, GPU

Ship features like STT/TTS pipelines, OCR, text-to-image, and hosted GPU inference — similar surface to Dibbly, Paperport, and Winsta-style media stacks.

Speech-to-text, TTS, transcription, multilingual flows
OCR, text-to-image (ComfyUI, Replicate), face swap patterns
RunPod, FAL.ai, Hugging Face, Ollama integrations
Queues, quotas, and safe rollout behind feature flags

Feature packs or media pipeline hardening

STT / TTS OCR ComfyUI GPU

💬 Chat about this service

Data & events

Event-driven systems & data pipelines

High-throughput patterns: Kafka-style messaging, CDC, and service boundaries for systems that must scale without losing consistency.

Apache Kafka, async consumers, backpressure-aware design
Debezium CDC patterns where applicable
Service decomposition and contract-first APIs
Operational playbooks for your SRE or platform team

Architecture + implementation slices

Kafka Event-driven PostgreSQL

💬 Chat about this service

Cloud & reliability

Cloud, DevOps & platform hardening

Docker and Kubernetes-oriented delivery, CI/CD, Nginx, AWS/GCP primitives, and observability — production paths from years shipping containerized backends.

Docker, Kubernetes, Nginx, VPS and cloud layouts
GitHub Actions CI/CD, environments, secrets hygiene
AWS EC2/S3/Lambda, GCP touchpoints as needed
Sentry and logging hooks for triage-friendly ops

Infra milestones or hardening sprints

Docker Kubernetes CI/CD AWS / GCP

💬 Chat about this service

Healthcare & compliance-aware

Secure backends for regulated domains

Experience from HIPAA-oriented diagnostic reporting (PathHub-style): access control, audit-friendly flows, and careful handling of sensitive data — scoped to your legal requirements.

Role-based access, session hardening, audit trails
Secure file and imaging workflows where applicable
Collaboration with your compliance/legal stakeholders
Documentation suitable for security review

Discovery required · scoped with your policies

Django PostgreSQL RBAC

💬 Chat about this service

Rescue & review

Performance, security & cost audit

Short, opinionated review of your AI and backend stack: latency, token spend, GPU vs CPU choices, auth/webhooks/secrets — you get a prioritized fix list.

Slow RAG paths, redundant LLM calls, caching wins
Right-size infra and model routing for unit economics
Security pass: auth, webhooks, secrets, headers
Optional follow-up implementation milestones

Compact audit window · optional implementation after

Review Cost Sentry

💬 Chat about this service

How freelance projects run

Transparent steps so stakeholders know what happens after first contact

Brief & fit

You send goals, stack, timeline, and any constraints (compliance, hosting region, languages). I reply with clarifying questions and whether I’m the right fit.

Proposal & milestone plan

Written scope: deliverables, acceptance checks, weekly rhythm, and pricing (fixed phases or retainer). No surprise scope creep without a change request.

Build, demo, ship

Incremental PRs or repo access, short Loom-style demos when useful, and documentation so your team can operate the system.

Handoff & optional care window

Knowledge transfer, backlog grooming, and optional post-launch support for tuning prompts, evals, and monitoring.

FAQ — hire a freelance AI & backend engineer

Common questions from founders and engineering leads (also marked up for rich results)

What freelance AI and backend work do you take?

Production-focused builds: agentic workflows, RAG and retrieval design, LLM orchestration and tool-calling, FastAPI and Python backends, microservices, async workers, vector search, and integrations such as Stripe and model hosting (RunPod, FAL.ai, etc.). I can pair with your Next.js app when needed.

Do you work with international clients remotely?

Yes. I am based in Nepal and collaborate with teams globally. English communication via email, WhatsApp, Slack, or your stack.

How do you price freelance projects?

Usually fixed milestones or a monthly retainer after discovery. Price depends on complexity, SLAs, compliance (for example healthcare), GPU inference, and multi-tenant SaaS needs. Email a concise brief for a tailored quote.

Can you join an existing codebase?

Yes. I extend existing FastAPI, Django, or Node services, ship AI features behind flags, and document APIs and operations so your team retains ownership.

Where can I see projects and employment history?

See the main portfolio for WinstaAI, Dibbly, Paperport, PathHub, stack depth, and open-source templates.

Do you sign an NDA?

Yes, standard mutual NDAs and contractor agreements are fine subject to reasonable terms.

What time zones do you overlap with?

I schedule overlap hours with US and EU teams where needed; async updates keep momentum between meetings.