Senior AI Full Stack Engineer (Contract)

Company Description

BIMora builds applied AI systems that integrate:

• Large Language Models (LLMs)

• Agentic orchestration workflows

• Retrieval-Augmented Generation (RAG)

• Structured tool-calling pipelines

• Secure multi-system integrations

We focus on production-grade AI infrastructure that supports real operational workflows and we are building modular AI platforms designed for scalability and long-term evolution.

Role Description

We are looking for a senior-level AI systems engineer who can design and implement reliable, production-ready LLM applications.

You will work directly with the Managing Director (Product & Technical Lead) to architect and build:

• Multi-agent orchestration systems

• RAG-based knowledge pipelines

• Secure backend APIs

• Execution-traceable AI workflows

• Modular AI infrastructure for future expansion

This role requires strong ownership. You must be capable of making architectural decisions and executing independently.

Key Responsibilities

LLM & AI Engineering

• Design and implement RAG pipelines (chunking, embedding, retrieval tuning)

• Build structured tool-calling workflows with validation layers

• Implement agentic orchestration (LangGraph or equivalent frameworks)

• Design memory and context management strategies

• Reduce hallucination through grounding and output enforcement

• Optimize for token efficiency, latency, and cost

Backend Development

• Build modular APIs using Python (FastAPI preferred)

• Design and manage relational databases (PostgreSQL)

• Implement authentication and role-based access control

• Integrate third-party APIs (Google, Microsoft, etc.)

• Implement structured logging and execution tracing

Deployment & Production

• Deploy scalable services to AWS / Azure / GCP

• Manage environment separation (dev / staging / production)

• Implement monitoring and reliability safeguards

• Ensure secure data handling and API key management

Qualifications

• 3+ years backend development experience
• 1+ year building LLM-based production systems
• Proven experience implementing RAG pipelines
• Experience with vector databases (Pinecone, Weaviate, Supabase, etc.)
• Experience with LangChain / LangGraph or equivalent orchestration tools
• Strong Python proficiency
• Experience with REST API design
• Database schema design experience (PostgreSQL)
• Experience deploying production systems to cloud

Engagement Type:

Part-Time Contract

Duration:

4-5 months (renewable based on performance and project continuity)

Salary Rate:

RM 150 - RM 200 / hour (Depends on experience)

60 - 80 hours / month

Start Date:

Flexible (Immediate preferred)