Job VC
Senior AI Engineer (Python)
Technologies
Description
We are looking for a Senior AI Engineer (Python) to join a funded US-based AI startup building next-generation infrastructure intelligence solutions for water utilities across North America.
This is a hands-on engineering role focused on integrating and scaling
LLM-powered
systems in production. You will work on agentic workflows, AI orchestration services, RAG pipelines, and real-time AI-driven functionality within a geospatial analytics platform.
Project
— an AI-driven platform that helps public utilities predict infrastructure failures (such as water pipe bursts) and optimize maintenance planning using machine learning, geospatial analysis, and municipal infrastructure data. The product is already used by government organizations and utility providers across North America.
Requirements:
5+ years of professional software engineering experience
Strong Python development experience
Hands-on experience with FastAPI or similar backend frameworks
Experience integrating OpenAI, Anthropic, or AWS Bedrock APIs
Solid understanding of RAG and vector search patterns
Experience with AI frameworks such as LangGraph, LangChain, MLflow, or similar
Experience building production-grade AI/LLM applications
Strong understanding of Docker and cloud-native environments
Experience with PostgreSQL
AWS experience
Upper-Intermediate English or higher
Nice to Have:
Experience with gRPC / protobuf
Experience deploying open-source LLMs (Llama or similar)
Experience with agentic workflows and tool-calling systems
GIS or geospatial systems exposure
MLOps or AI infrastructure experience
Responsibilities:
Integrate external LLM APIs such as OpenAI, Anthropic, and Bedrock
Extend agentic workflows and ReAct-loop systems
Build AI-powered backend functionality for real-time geospatial applications
Develop functional primitives and tool-calling capabilities for LLM agents
Design and improve RAG pipelines and evaluation systems
Analyze latency, response quality, and AI system cost trade-offs
Collaborate with product and domain experts on evaluation datasets and AI workflows
We offer:
Vacation (up to 20 working days)
Sick leaves (10 working days)
National Holidays as time off (up to 11 days)
Medical reimbursement/insurance after 3 months
Online English courses
Flexible working schedule, remote
Direct cooperation with the customer
Communication with Top/Senior level specialists to strengthen your hard skills
Online/offline teambuildings
Volunteering culture development and support
This is a hands-on engineering role focused on integrating and scaling
LLM-powered
systems in production. You will work on agentic workflows, AI orchestration services, RAG pipelines, and real-time AI-driven functionality within a geospatial analytics platform.
Project
— an AI-driven platform that helps public utilities predict infrastructure failures (such as water pipe bursts) and optimize maintenance planning using machine learning, geospatial analysis, and municipal infrastructure data. The product is already used by government organizations and utility providers across North America.
Requirements:
5+ years of professional software engineering experience
Strong Python development experience
Hands-on experience with FastAPI or similar backend frameworks
Experience integrating OpenAI, Anthropic, or AWS Bedrock APIs
Solid understanding of RAG and vector search patterns
Experience with AI frameworks such as LangGraph, LangChain, MLflow, or similar
Experience building production-grade AI/LLM applications
Strong understanding of Docker and cloud-native environments
Experience with PostgreSQL
AWS experience
Upper-Intermediate English or higher
Nice to Have:
Experience with gRPC / protobuf
Experience deploying open-source LLMs (Llama or similar)
Experience with agentic workflows and tool-calling systems
GIS or geospatial systems exposure
MLOps or AI infrastructure experience
Responsibilities:
Integrate external LLM APIs such as OpenAI, Anthropic, and Bedrock
Extend agentic workflows and ReAct-loop systems
Build AI-powered backend functionality for real-time geospatial applications
Develop functional primitives and tool-calling capabilities for LLM agents
Design and improve RAG pipelines and evaluation systems
Analyze latency, response quality, and AI system cost trade-offs
Collaborate with product and domain experts on evaluation datasets and AI workflows
We offer:
Vacation (up to 20 working days)
Sick leaves (10 working days)
National Holidays as time off (up to 11 days)
Medical reimbursement/insurance after 3 months
Online English courses
Flexible working schedule, remote
Direct cooperation with the customer
Communication with Top/Senior level specialists to strengthen your hard skills
Online/offline teambuildings
Volunteering culture development and support