Software Application Engineer – AI & LLM

Om tjänsten

Malezan Group AB är en strategisk kompetenspartner som kopplar samman ledande europeiska företag med spetskompetens. Vi bygger på en stark grund av global resurs outsourcing – där vi framgångsrikt har levererat skickliga talanger från Afrika till den europeiska marknaden.

I takt med att behovet av avancerad teknologi ökar skalar vi nu upp vår närvaro i Sverige. Vi expanderar vårt erbudande genom att bygga ett starkt lokalt team inom Machine Learning (ML) och Artificiell Intelligens (AI). Med en unik kombination av global räckvidd och lokal expertis hjälper vi företag att driva sin digitala transformation och utveckla framtidssäkrade AI-lösningar.

We are looking for a talented Software Application Engineer specializing in AI & LLMs to join our team. In this role, you will bridge the gap between cutting-edge artificial intelligence and robust production software. You will design, build, and deploy intelligent applications that leverage Large Language Models (LLMs), generative AI tools, and advanced data architectures to solve real-world problems.

If you are passionate about building scalable AI workflows, prompt engineering, agentic frameworks, and production-ready AI services, we want to hear from you.

Key Responsibilities

Design & Architecture: Build and maintain scalable, production-grade AI-powered applications, microservices, and API integrations.

LLM Integration: Implement state-of-the-art Large Language Models using frameworks like LangChain, LlamaIndex, or native APIs (OpenAI, Anthropic, open-source models like Llama/Mistral).

RAG & Vector Databases: Architect and optimize Retrieval-Augmented Generation (RAG) pipelines and integrate vector databases (e.g., Pinecone, Weaviate, Qdrant, Chroma).

Prompt Engineering & Agentic Systems: Design, test, and optimize prompt strategies, agentic workflows, and tool-calling models for high accuracy and low latency.

Performance & Optimization: Monitor, evaluate, and fine-tune model outputs, cost, latency, and reliability using LLM evaluation frameworks (e.g., Ragas, LangSmith).

Cross-Functional Collaboration: Partner with product managers, data science teams, and frontend engineers to translate business requirements into intelligent software features.

Qualifications & Skills

Required:

Education: Bachelor’s degree in Computer Science, Software Engineering, Data Science, or equivalent practical experience.

Experience: 3+ years of professional software engineering experience, with at least 1–2 years focused on building applications with LLMs or machine learning systems.

Programming Languages: High proficiency in Python and/or TypeScript / JavaScript / Go / C++.

AI/LLM Ecosystem: Direct experience with LLM APIs, LangChain, LlamaIndex, function calling, and prompt orchestration.

Data & Storage: Hands-on experience with vector databases and relational/NoSQL databases (PostgreSQL, Redis, MongoDB).

Cloud & DevOps: Familiarity with AWS, GCP, or Azure, along with containerization tools (Docker, Kubernetes) and CI/CD pipelines.

Preferred / Nice-to-Have:

Experience fine-tuning open-source LLMs (LoRA, QLoRA) or working with model hosting frameworks (vLLM, Ollama, Hugging Face).

Knowledge of AI safety, guardrails (e.g., NeMo Guardrails), hallucination reduction, and evaluation techniques.

Experience building agentic architectures (AutoGPT, CrewAI, LangGraph).

Benefits

Competitive salary and performance-based bonuses

Comprehensive health, dental, and vision insurance

How to Apply

Click Apply Now and submit your resume along with a link to your GitHub profile, portfolio, or recent AI projects you’ve built!

Tips for Posting on Indeed:

Salary Transparency: Indeed highlights postings that disclose compensation upfront.

Sponsorship/Work Authorization: Under the "Application Questions" tab on Indeed, add a custom screening question regarding work authorization (e.g., "Will you now or in the future require sponsorship for employment visa status?").

Assessment Tests: Enable Indeed's pre-screening tests for Python or Software Architecture to automatically filter top applicants.