AI Solutions Engineer: LLM-Powered APIs & Data Automation

gigalabs-private-ltd; Lahore; On-site; PKR 2,400,000 - 4,200,000; Full time

Job summary

gigalabs-private-ltd in Lahore (Johar Town, G4) seeks an experienced backend engineer to build AI-driven APIs and automate data workflows using FastAPI and n8n. You will ensure data quality for LLM pipelines, manage PostgreSQL databases with vector data, and design scalable microservices.

The role requires deep Python, API development, and experience with LLM integrations (LangChain/LlamaIndex) and OpenAI ecosystems. Onsite work with 12PM-9PM timings, 4–5 years of relevant experience.

Qualifications

• Hands-on proficiency in Python for data manipulation and backend logic.
• Experience building, documenting, and maintaining RESTful APIs using FastAPI and Flask.
• Ability to wrap data models and scripts into deployable microservices.
• Experience constructing LLM pipelines and agents to process text and data.
• Familiarity with OpenAI ecosystem and cost optimization strategies.
• Advanced SQL skills in PostgreSQL, including joins, window functions, and performance tuning.
• Experience with vector embeddings and vector similarity search in PostgreSQL for RAG implementations.
• Experience with n8n workflow automation for building complex, conditional workflows.
• Ability to design data models and store LLM interaction logs.

Responsibilities

• Develop AI-Driven APIs using FastAPI to serve data insights powered by LLMs.
• Automate business logic with autonomous n8n workflows.
• Ensure data quality for inputs to LLM pipelines and outputs.
• Maintain and optimize PostgreSQL for relational and vector data loads.

Skills

Python proficiency

API development

Microservices

LLM pipelines

Prompt engineering

Data modeling

n8n workflow automation

ETL/ELT

Tools

FastAPI

Flask

pgvector

Job description

gigalabs-private-ltd in Lahore (Johar Town, G4) seeks an experienced backend engineer to build AI-driven APIs and automate data workflows using FastAPI and n8n. You will ensure data quality for LLM pipelines, manage PostgreSQL databases with vector data, and design scalable microservices.

The role requires deep Python, API development, and experience with LLM integrations (LangChain/LlamaIndex) and OpenAI ecosystems. Onsite work with 12PM-9PM timings, 4–5 years of relevant experience.