AI Engineer

Company Description

Prometteur Solutions delivers cutting-edge technology-driven business solutions tailored for organizations across enterprise, government, and education markets. Committed to client satisfaction, the company combines highly-skilled professionals with global delivery capabilities to align technology solutions with business goals. With expertise in areas such as Enterprise Mobility, Web Development, UX/UI Design, and Software Consulting, Prometteur Solutions partners with a diverse range of industries including E-Commerce, Healthcare, Education, Media, and more. Leveraging modern technologies like React Native, Flutter, Node.js, and PHP, the company's mission is to build long-term client relationships by delivering meaningful and lasting business value.

Job Title:

AI Engineer (Applied AI / LLM)

Experience: 34 Years

Employment Type: Full-Time

Role Overview

We are looking for an AI Engineer with 2 years of hands-on experience building and delivering

production-ready AI solutions for real customers. This role is focused on Applied AI, meaning

building, shipping, and maintaining AI-powered features. The ideal candidate has a strong

foundation in AI/ML concepts, solid software engineering skills, and proven experience integrating

LLMs and AI services into scalable applications. You will work closely with product and

engineering teams to design, develop, and operate AI features that solve real business problems.

Key Responsibilities

AI Solution Design & Delivery

Understand business requirements and translate them into practical AI-driven solutions

Design and implement end-to-end AI workflows using existing models, SDKs, and APIs

Deliver customer-facing AI features with a strong focus on reliability, usability, and

performance

Backend & Integration

Build backend services and APIs for AI modules (language/framework agnostic)

Integrate AI services with existing systems, databases, and third-party tools

Collaborate with frontend engineers to ensure smooth integration and user experience

Quality, Reliability & Optimization

Improve AI output quality using:

Prompt engineering and prompt versioning

Structured outputs (JSON, schema-based responses)

Guardrails, validations, and fallbacks

Ensure production readiness by addressing:

Performance and latency optimization

Error handling, retries, monitoring

Cost optimization (token usage, caching, API efficiency)

Security & Maintainability

Follow responsible AI practices including data privacy and security basics

Maintain clean, well-documented, versioned AI components

Design systems that allow easy model/provider replacement when needed

Required Skills

Core Engineering Skills

Strong software engineering fundamentals (clean code, modularity, testing, API design)

Experience building production-grade backend services in any modern backend stack

Understanding of async/non-blocking patterns and scalable service design

Robust error handling and integration readiness

AI/ML & LLM Experience

Hands-on experience using LLM APIs such as OpenAI, Gemini, Anthropic, or similar

Experience using frameworks/tools such as LangChain, LlamaIndex, or equivalents

Strong understanding of prompt engineering and evaluation methodologies

Data & Storage

Experience working with unstructured datasets (PDFs, documents, text, OCR outputs)

Experience with vector stores/vector DBs: Pinecone, Weaviate, Chroma, FAISS, etc.

Working knowledge of relational DB concepts (SQL basics)

Backend Development

Experience building secure APIs (REST/GraphQL) with authentication and integrations

Ability to integrate AI modules into microservices / monolith architectures

Must-Have Experience

2 years in applied AI, AI engineering, or ML-driven software development

Proven record of delivering AI features used by real customers in production

Ability to share case studies demonstrating:

Problem statement

Solution approach

Technology stack

Business impact / user outcomes

Nice to Have

Experience with OCR and document intelligence systems

Speech-to-text and text-to-speech exposure

Experience deploying systems on AWS/GCP/Azure

Containerization experience (Docker fundamentals)

Exposure to monitoring/logging/MLOps best practices

What Success Looks Like

AI features are deployed and actively used by customers

Continuous improvement in AI quality, reliability, and cost efficiency

AI systems are scalable, maintainable, and aligned with product goal