An application made for this job — a tailored resume and cover letter that speak straight to the posting.
Zenika is seeking a software engineer consultant to design, build, and deploy AI-powered applications for clients, with a focus on reliable, production-grade pipelines. You’ll collaborate with client teams to implement end-to-end generative AI systems, orchestrate multi-agent workflows, and manage vector stores using Qdrant, Pinecone, Chroma, or PGVector.
You bring 3–8 years of software experience, strong Python skills, and hands-on cloud/DevOps know-how with Docker and Kubernetes, plus the
Let’s talk skills and passion first.
You thrive on building intelligent, robust systems and production-grade AI pipelines. You are a software engineer at heart who views AI models as powerful tools, but you possess a craftsman’s mindset—focusing on simplicity, performance, and ethical safety. You care deeply about system reliability, latency, and clean code. Whether you are optimizing a Retrieval-Augmented Generation (RAG) system, coordinating multi-agent workflows, or managing vector databases, you take pride in software that is highly maintainable under the hood and delivers real, measurable value to production environments.
As a consultant, you'll work on strategic client engagements. You will design, build, and deploy reliable AI-powered applications while collaborating closely with client engineering teams to:
Architect & Build: Design and develop end-to-end generative AI systems, utilizing LLMs, semantic search, and robust backend integrations (primarily in Python or TypeScript).
Agentic Workflows: Implement autonomous AI agents and multi-agent frameworks capable of executing complex, multi-step actions and tool calling.
Data & Vector Management: Structure, optimize, and maintain vector databases (e.g., Qdrant, Pinecone, Chroma, or PGVector) and advanced embedding/chunking strategies.
Evaluation & Guardrails: Design robust metrics to evaluate model performance (accuracy, latency, costs) and establish security guardrails to mitigate hallucinations and data leaks.
Engineering Standards: Apply solid software engineering practices to AI development, including unit testing, test-driven development (TDD), rigorous code reviews, and living documentation.
Cloud & Automation: Deploy cloud-native AI applications using Docker, Kubernetes, and cloud-native AI services (AWS Bedrock, GCP Vertex AI, or Azure OpenAI).
Leadership: Help clients navigate the AI hype by identifying high-impact use cases, establishing best practices, and mentoring client engineering teams to become self-sufficient.
Experience: 3-8 years of professional software development experience, with a solid focus on building and deploying AI/LLM-integrated applications.
AI/LLM Application Stack: Hands-on experience with orchestration libraries such as LangChain, LangGraph, LlamaIndex, or CrewAI.
Software Craftsmanship: A passion for clean code (SOLID, DRY), strong proficiency in Python, and writing robust test suites (e.g., PyTest).
Data & Vector Stores: Direct experience working with relational databases and vector search engines.
Cloud & DevOps: Hands-on experience with Docker, CI/CD pipelines, and cloud environments (AWS, GCP, or Azure).
Consulting Mindset: Comfort working with diverse clients, translating complex AI concepts to non-technical stakeholders, and adapting quickly to different team cultures.
Founded by developer Carl Azoury, Zenika is a consultancy built around community, transparency, and craftsmanship. Our passionate team advises clients with expertise in open-source technologies and modern solutions.
Work with a global client base across 11 locations, accessing 28,000+ Zenika-led training sessions worldwide
Partner with industry leaders like Google Cloud and Scrum.org, and engage in research, open-source work, and conferences outside client projects
Connect and grow with fellow experts through our annual TechnoZaures, sharing skills and knowledge