Artificial Intelligence Engineer - LLM

Description
Wednesday is a global engineering consultancy.
We partner with ambitious companies to build AI-native products, modernize data platforms, and accelerate software development.
We work at the early and most ambiguous stages of product development where craft, clarity, and execution speed determine success.
Our teams include engineers, designers, and product managers who care deeply about the work they do.
We treat software like a craft, and our clients like long-term collaborators.
What Youll Do
As an AI Engineer at Wednesday, youll design and build production-ready AI systems using state-of-the-art language models, vector databases, and modern AI frameworks.
Youll own the full lifecycle of AI features from prototyping and prompt engineering to deployment, monitoring, and optimization.
Youll work closely with product and engineering teams to ensure our AI solutions deliver real business value at scale.
Your Responsibilities
System Architecture & Development :

• Architect and implement AI applications leveraging transformer-based LLMs, embeddings, and vector similarity techniques.
• Build modular, maintainable codebases using Python and AI Generation & Semantic Search :

• Design and deploy RAG systems with vector databases such as Pinecone, Weaviate, or Chroma to power intelligent document search and knowledge retrieval.
  

LLM Integration & Optimization

• Integrate with LLM platforms (OpenAI, Anthropic) or self-hosted models (Llama, Mistral), including prompt engineering, fine-tuning, and model evaluation.
• Experience with AI orchestration tools (LangFlow, Flowise), multimodal models, or AI safety and evaluation frameworks.
  

AI Infrastructure & Observability

• Develop scalable AI pipelines with proper monitoring, evaluation metrics, and observability to ensure reliability in production environments.
  

End-to-End Integration & Rapid Prototyping

• Connect AI backends to user-facing applications; prototype new AI features quickly using frontend frameworks Collaboration :
• Partner with product managers, designers, and fellow engineers to translate complex business requirements into robust AI solutions.

  Looking to get Placed? Try our Placement Guarantee Plan

  Get Hired
  
  

Youll Thrive In This Role If You

• Have 3 to 5 years of experience building production AI/ML systems at a consulting or product-engineering firm.
• Possess deep understanding of transformer architectures, vector embeddings, and semantic search.
• Are hands-on with vector databases (Pinecone, Weaviate, Chroma) and RAG pipelines.
• Have integrated and optimized LLMs via APIs or local deployment.
• Are proficient in Python AI stacks (LangChain, LlamaIndex, Hugging Face).
• Have built backend services (FastAPI, Node.js, or Go) to power AI features.
• Understand AI UX patterns (chat interfaces, streaming responses, loading states, error handling).
• Can deploy and orchestrate AI systems on AWS, GCP, or Azure with containerization and orchestration tools.
  

Bonus : Advanced React/Next.js skills for prototyping AI-driven UIs.
(ref:hirist.tech)