Python AI Engineer

Techolution LLC; India; A distancia; INR 1.200.000 - 2.000.000; Jornada completa

Descripción de la vacante

Techolution LLC is seeking a Python AI Engineer for a remote, full-time role. You will build backend services and APIs in Python, focusing on microservices, asynchronous patterns, and scalable architectures.

You will work with LLMs, RAG pipelines, embeddings, vector databases, and AI agents, collaborating with senior engineers to deliver robust AI-powered applications.

Formación

• Strong Python backend development fundamentals.
• Experience building APIs with FastAPI or Flask.
• Proficient in Python asynchronous programming patterns.
• Experience with microservices and REST APIs.
• Familiar with data validation using Pydantic.
• Hands-on exposure to Generative AI, LLMs, and RAG pipelines.
• Experience with NoSQL and caching (Redis).
• Git for version control and collaborative development.
• Knowledge of cloud environments (GCP or AWS).

Responsabilidades

• Develop and maintain backend services and APIs using Python and FastAPI/Flask.
• Write clean, reusable code following OOP principles.
• Develop and integrate microservices and REST APIs.
• Implement data validation with Pydantic.
• Integrate Generative AI capabilities into applications.
• Work with LLMs, RAG pipelines, embeddings, and AI agents/orchestration.
• Integrate AI services through APIs and SDKs.
• Use NoSQL databases for AI workloads.
• Implement Redis caching to improve performance.
• Utilize asynchronous Python for API calls and DB ops.
• Collaborate with senior engineers and teams throughout the lifecycle.
• Participate in code reviews and best practices.

Conocimientos

Python

FastAPI/Flask

OOP

Pydantic

Microservices

REST APIs

Asynchronous programming

NoSQL

Redis caching

Git

GCP/AWS

LLMs/RAG

Herramientas

FastAPI

Flask

Pydantic

Redis

Git

GCP

AWS

Descripción del empleo

We are looking for a Python AI Engineer with a strong foundation in Python backend development and hands‑on exposure to Generative AI.

The ideal candidate will have experience building APIs and backend services using Python, along with a good understanding of microservices, asynchronous programming, NoSQL databases, caching, and cloud environments.

You will work on AI‑powered applications involving LLMs, RAG, embedding models, vector databases, and AI agents, while collaborating with senior engineers to build scalable and reliable solutions.

Title : Python AI Engineer

Location :Remote Work

Employment Type: Full-time

Exp Range : 1-4 years

Key Responsibilities

• Develop and maintain backend services and APIs using Python and FastAPI/Flask.
• Build clean, reusable, and maintainable code using Object‑Oriented Programming principles.
• Develop and integrate microservices and REST APIs.
• Implement data validation and serialization using Pydantic.
• Develop and integrate Generative AI capabilities into applications.
• Work with LLMs, RAG pipelines, embedding models, vector databases, and AI agents/orchestration.
• Integrate LLMs and AI services through APIs and SDKs.
• Work with NoSQL databases for application and AI‑related workloads.
• Implement Redis and caching mechanisms to improve application performance.
• Use Python's asynchronous programming capabilities for API calls, database operations, and LLM requests.
• Use Git for version control, branching, code reviews, and collaborative development.
• Work with GCP or AWS environments and assist with deployments, troubleshooting, log analysis, and application monitoring.
• Debug technical issues, identify root causes, and implement effective solutions.
• Collaborate with senior engineers and technical teams throughout the development lifecycle.
• Participate in code reviews and follow engineering best practices.

Qualifications:

• Strong programming skills in Python with a solid understanding of software development fundamentals.
• Hands‑on experience developing APIs using FastAPI or Flask.
• Strong understanding of Object‑Oriented Programming (OOP) and writing clean, maintainable, and reusable code.
• Experience with Pydantic or similar frameworks for data validation and serialization.
• Understanding of microservices architecture and REST API development.
• Strong problem‑solving, debugging, and analytical skills.
• Hands‑on exposure to Generative AI, including: Large Language Models (LLMs) , Retrieval‑Augmented Generation (RAG) , Embedding models, Vector databases ,LLM/API integrations, AI agents and orchestration
• Good understanding of Git and version control, including branching and collaborative development.
• Understanding of NoSQL databases and flexible‑schema data modeling.
• Basic understanding of Redis and caching concepts.
• Understanding of asynchronous programming in Python, including async/await.
• Exposure to GCP or AWS, with a basic understanding of application deployment, troubleshooting, and logs.

Nice to Have:

• Experience with Docker and containerization.
• Exposure to CI/CD pipelines and automated build and deployment processes.
• Understanding of system design and scalable application architectures.
• Exposure to message queues and event‑driven architectures, such as Kafka, RabbitMQ, or Google Pub/Sub.
• Understanding of API security, including authentication, authorization, JWT/OAuth, and secrets management.
• Exposure to LLM evaluation and optimization.
• Understanding of prompt optimization, latency optimization, token usage, cost optimization, and hallucination reduction.