Skip to main content
Madiff

Tech Lead Python GenAI Developer - Remote

1w

Madiff

Remote · Full-time · $200,000 – $260,000

About this role

This is a remote position for a Tech Lead Python GenAI Developer to anchor the backend engineering stream for next-generation GenAI products. You will be central to shaping architecture and delivery for LLM-driven assistants, enterprise knowledge platforms, document intelligence solutions, and conversational AI systems.

Day-to-day, you will lead the design, development, integration, and optimisation of GenAI services across multiple business units. You will drive RAG pipeline design using LangChain and LangGraph, define ingestion and embedding workflows, and integrate vector databases like Pinecone, Chroma, and Weaviate.

You will collaborate closely with frontend and platform teams to ensure smooth API consumption, establish standards for prompt lifecycle management and token strategy, and lead evaluation cycles to reduce latency and achieve production readiness. Your technical leadership will guide a team of engineers building Python microservices with FastAPI and Pydantic.

This role offers the opportunity to shape the backend architecture of LLM products, including routing, retrieval, memory, and evaluation flows, while promoting best practices in code quality, observability, DevOps, and cloud deployment. You will help define how GenAI capabilities are scaled and delivered across the organisation.

Requirements

  • 6+ years of Python engineering experience with strong backend foundations
  • Proven commercial experience building GenAI or LLM-centric systems
  • Hands-on expertise with FastAPI, Pydantic, LangChain, LangGraph
  • Strong understanding of embeddings, similarity search, and vector databases
  • Experience running GenAI workloads in production environments
  • Ability to lead engineers, make architectural decisions, and coordinate delivery

Responsibilities

  • Provide technical leadership for Python-based GenAI services
  • Design backend architecture for LLM products including routing, retrieval, memory and evaluation flows
  • Build and optimise Python microservices exposing GenAI capabilities (FastAPI, Pydantic)
  • Drive RAG pipeline design using LangChain and LangGraph
  • Define ingestion, chunking and embedding workflows for enterprise knowledge systems
  • Integrate vector databases (Pinecone, Chroma, Weaviate)
  • Establish standards for prompt lifecycle management, token strategy, and model selection
  • Lead evaluation cycles, latency reduction, and production-readiness measures

Benefits

  • Remote work arrangement
  • Opportunity to shape architecture for next-generation GenAI products
  • Lead a team building cutting-edge LLM-driven assistants and enterprise knowledge platforms