Senior Polyglot Engineer

Fanisko; United States; On-site; USD 120,000 - 160,000; Full time

Job summary

Fanisko is seeking a versatile Senior Polyglot Engineer to lead the development of AI-powered platforms. You will architect retrieval-augmented generation systems, optimize workflows, and build user interfaces that facilitate complex AI interactions. Ideal candidates possess strong skills in Python, FastAPI, and React, with a deep understanding of LLMs and data architecture. The role emphasizes backend excellence and cloud infrastructure management, particularly within AWS environments. Apply to be part of pioneering AI technology development.

Qualifications

• Deep understanding of LLMs (OpenAI, Anthropic, Llama 3) and prompt engineering.
• Hands-on experience with RAG (Retrieval-Augmented Generation) and vector embeddings.
• Expertise in Python with AsyncIO and Type Hinting.

Responsibilities

• Design and deploy production-grade RAG pipelines and workflows.
• Build high-performance, asynchronous microservices using Python and FastAPI.
• Develop responsive, state-driven interfaces in React to handle complex AI outputs.

Skills

MongoDB aggregation

React

Python

FastAPI

AWS

Docker

Tools

LangChain

FastAPI

MongoDB

React.js

Job description

We are looking for a versatile Senior Polyglot Engineer to lead the development of our next-generation AI-powered platforms. This is not a standard full-stack role; you will be responsible for architecting retrieval-augmented generation (RAG) systems, optimizing LLM workflows, and building seamless user interfaces that make complex AI interactions intuitive. You should be as comfortable tuning a MongoDB aggregation pipeline as you are designing a React component or optimizing an embedding search.

Key Responsibilities

• End-to-End AI Engineering: Design and deploy production-grade RAG pipelines and Agentic workflows using frameworks like LangChain or LlamaIndex.
• Backend Excellence: Build high-performance, asynchronous microservices using Python and FastAPI, ensuring secure and scalable API design.
• Frontend Sophistication: Develop responsive, state-driven interfaces in React to handle complex AI outputs (streaming responses, citations, and interactive data).
• Data Architecture: Manage and optimize data flows across MongoDB (NoSQL) and Vector Databases (e.g., Pinecone, Milvus, or Weaviate) for semantic search.
• Cloud Infrastructure: Architect and maintain scalable AI services on AWS, leveraging services like Lambda, SageMaker, Bedrock, and ECS/EKS.
• AI Observability: Implement monitoring for LLM performance, including latency, token usage, cost optimization, and hallucination detection.

Qualifications

• Deep understanding of LLMs (OpenAI, Anthropic, Llama 3) and prompt engineering.
• Hands-on experience with RAG (Retrieval-Augmented Generation) and vector embeddings.
• Experience with AI orchestration (LangChain, LangGraph, or CrewAI).
• Expertise in Python (AsyncIO, Type Hinting, Pydantic).
• High proficiency in FastAPI for building RESTful and WebSocket-based services.
• Strong experience with MongoDB (Schema design, indexing, and aggregation).

3. Frontend

• Strong command of React.js and modern state management (Zustand, Redux, or React Query).
• Experience building interfaces for real-time data streaming and AI-driven UX.
• Proficiency in AWS ecosystem (S3, EC2, IAM, and AI-specific services).
• Experience with Docker and CI/CD pipelines for automated testing and deployment.