AI Backend Engineer (Python) — Forward Deployed
Summary
Forward-deployed Python backend engineer who embeds with a banking client's AI platform team to build, ship, and hand off LLM-based agents on AWS using LangGraph, LiteLLM, and Langfuse, then rotates to the next team. Core stack: Python/FastAPI, AWS deployment (containers, CI/CD), and LLM evals/observability.
🚀 Join Our Remote Data Products & Machine Learning Startup! 🚀
At Muttdata, we build innovative Data Products and Machine Learning solutions that help companies solve complex business challenges. As a fast-growing, remote-first startup, we're passionate about technology, collaboration, and continuous learning.
We're looking for a proactive, technically strong AI Backend Engineer (Python) — Forward Deployed to join our team 🐶🚀. You'll work on a strategic project for one of our banking clients, embedded within the bank's AI platform team, taking LLM-based agents into production across the bank's business units.
This is an embedded role: you join a team that has an agent to build or deploy, build it on top of the platform's scaffolding (LangGraph, LiteLLM, Langfuse), take it to production through the bank's controls, and leave the team able to operate it on their own. Once that agent is live, you move on to the next team. What you learn in each rotation feeds back into the platform as improvements to the template, observability, and deployment process.
This role requires strong ownership, solid architectural judgment, and the ability to build systems that are secure, performant, and built to scale. You'll collaborate closely with cross-functional teams in a fast-paced, high-standards environment typical of the financial industry.
🚀 What We Do
- Leveraging our expertise, we build modern Machine Learning systems for demand planning and budget forecasting.
- Developing scalable data infrastructures, we enhance high-level decision-making, tailored to each client.
- Offering comprehensive Data Engineering and custom AI solutions, we optimize cloud-based systems.
- Using Generative AI, we help e-commerce platforms and retailers create higher-quality ads, faster.
- Building deep learning models, we enhance visual recognition and automation for various industries, improving product categorization, quality control, and information retrieval.
- Developing recommendation models, we personalize user experiences in e-commerce, streaming, and digital platforms, driving engagement and conversions.
🌟 Our Partnerships
- Amazon Web Services
- Astronomer
- Databricks
🌟 Our Values
- 📊 We are Data Nerds
- 🤗 We are Open Team Players
- 🚀 We Take Ownership
- 🌟 We Have a Positive Mindset
Responsibilities 🤓
- Build agents on top of the platform's scaffolding, including tool calling, integration with the bank's internal APIs, state and conversation management, and guardrails.
- Take each agent to production on AWS: containers, CI/CD, secrets, permissions, networking, and the bank's security controls.
- Define and run evals before going to production, and monitor with Langfuse once deployed (quality, latency, cost).
- Unblock technical and process issues together with the Identity, Security, DevSecOps, and Networking teams.
- Leave documentation and runbooks so the team can operate the agent independently, transferring knowledge before rotating to the next team.
- Feed what you learn in each rotation back into the platform: improvements to the agent template, the deployment pipeline, and observability.
Required Skills 💻
- At least one LLM-based agent or system taken to production and operated, using LangGraph or an equivalent framework.
- 4+ years of backend experience in Python, with production services (FastAPI or another async framework).
- Ability to independently take a service from the repo to production on AWS: containers, CI/CD, and observability.
- Experience with LLM evaluation (evals, tracing, hallucination control) and agent observability (Langfuse or similar).
- Daily use of AI development tools (GitHub Copilot, Claude Code, Cursor).
- Ability to join a new team, quickly understand its context, and unblock issues with both technical and business stakeholders.
- Clear communication and a habit of documenting and handing off what you build.
Nice to have 💻
- Experience in banking or fintech.
- Kubernetes and Terraform.
- API security (OAuth2/JWT).
- RAG and vector databases.
- Building your own MCP servers.
- Spec-Driven Development.
- Prior experience as an embedded client consultant or in a forward-deployed role.
🎁 Perks
- 🌍 Remote-first culture – work from anywhere!
- 🚀 In-Company English Lessons.
- 💪 Wellhub or sports club stipend to stay active
- 🚀 AWS, DBT, Google Cloud, Azure & Databricks certifications fully covered
- 🍕 Food credits via Pedidos Ya – because great work deserves great food.
- 🎂 Birthday off + an extra vacation week (Mutt Week! 🏖️)
- 🤝 Referral bonuses – help us grow the team & get rewarded!
- ✈️🏝️ Annual Mutters' Trip – an unforgettable getaway with the team!
- 👶 Monthly Childcare Reimbursement – Because supporting families matters too
Skills
- AI
- API
- Api Security
- Automation
- AWS
- Azure
- CI/CD
- Claude Code
- Cloud
- Data Engineering
- Databricks
- dbt
- Deep Learning
- DevSecOps
- E-commerce
- FastAPI
- Fintech
- GCP
- Generative AI
- GitHub
- Github Copilot
- JWT
- Kubernetes
- LangGraph
- LLM
- Machine Learning
- MCP
- Networking
- OAuth
- Observability
- Python
- Terraform
- Vector Databases
As published by lever · 11 questions · 9 written answers
Basics
Resume/CV, Full name, Email, Phone, Current location, Current company, LinkedIn URL, GitHub URL, Other URL
Pick from a list (2)
- Como nos conociste? optional
- Nivel de ingles optional
Written answers (9)
- Contanos sobre tu experiencia desarrollando aplicaciones backend en Python. ¿Qué frameworks utilizaste (FastAPI, Django, Flask, etc.) y cuántos años trabajaste con ellos? optional
- Implementaste un agente o sistema con LLMs que hayas llevado a producción y operado, con LangGraph o un framework equivalente?
- ¿Qué experiencia tenés desarrollando y manteniendo microservicios en producción? Contanos brevemente sobre las arquitecturas con las que trabajaste. optional
- ¿Trabajaste con FastAPI (o algún framework asíncrono similar)? Contanos en qué proyectos lo utilizaste y cuál fue tu rol. optional
- ¿Cuál es tu experiencia utilizando Docker, Kubernetes, pipelines de CI/CD y herramientas de observabilidad? ¿En qué cloud trabajaste principalmente? optional
- ¿Tuviste experiencia integrando modelos de IA Generativa (LLMs) en aplicaciones backend? Si es así, contanos qué tecnologías utilizaste (RAG, LangGraph, LiteLLM, streaming, OpenAI, Anthropic, etc.). optional
- Formacion Academica optional
- Salario pretendido en pesos bruto (ARS) optional
- Residis en Argentina? Es requisito excluyente para esta vacante optional
