Intermediate Software Engineer – Artificial Intelligence, AI

Role Overview

• Design and build AI-driven features for our domain services platform using Python and Golang.
• Integrate and fine-tune open-source models such as LLaMA 3.2 and similar cutting-edge architectures via tools like Ollama.
• Research, evaluate, and implement emerging AI technologies that align with our vision for smarter, more intuitive products and services.
• Collaborate with internal stakeholders and fellow engineers to rapidly prototype and iterate on machine learning and LLM-based features.
• Contribute to a modern AI development stack, ensuring scalability, performance, and ethical usage of models.
• Actively participate in the open-source ecosystem and bring relevant tools and techniques back to the team.

Requirements

• Bachelor’s degree in Software Engineering, Computer Science, or a related field
• 3+ years of professional software engineering experience in production environments
• Strong proficiency in Python and Golang
• Solid foundation in software design principles, patterns, and service-oriented architecture
• Experience contributing to scalable systems and component-level architecture
• Ability to design and build RESTful APIs for model serving and AI-enabled workflows
• Working knowledge of relational/SQL databases (preferably PostgreSQL) and data modeling for AI use cases
• Strong understanding of modern LLM concepts, including transformer architectures and attention mechanisms
• Hands-on experience adapting and deploying open-source models (e.g., LLaMA, Mistral, Mixtral) using tools like Ollama or Hugging Face Transformers
• Experience with fine-tuning techniques (e.g., LoRA, QLoRA, PEFT) for domain-specific adaptation
• Proficiency in prompt engineering (few-shot, chain-of-thought, structured outputs)
• Familiarity with model serving patterns for efficient, scalable inference
• Experience designing and implementing Retrieval-Augmented Generation (RAG) pipelines end-to-end
• Hands-on experience with vector databases (e.g., pgvector, Pinecone, Weaviate)
• Familiarity with embedding models, chunking strategies, and semantic search patterns
• Understanding of data pipelines for ingestion, transformation, and inference result storage
• Familiarity with Model Context Protocol (MCP) server design patterns
• Experience with agent orchestration frameworks (e.g., LangChain, LangGraph)
• Understanding of tool use, function calling, and multi-step reasoning in LLM workflows
• Experience with LLM evaluation frameworks (e.g., RAGAS, promptfoo, or custom pipelines)
• Familiarity with observability and tracing tools (e.g., LangSmith, Helicone)
• Comfort with structured logging, metrics, and alerting for AI workloads
• Experience with containerization and cloud-native deployment (preferably AWS)
• Familiarity with Kubernetes or EKS for scaling model-serving workloads
• Understanding of GPU considerations for inference (quantization, batching, memory trade-offs)
• Active interest in the open-source AI ecosystem
• Strong collaboration and communication skills across technical and business teams
• Enthusiasm for emerging AI technologies with a practical, delivery-focused mindset.

Tech Stack

• AWS
• Cloud
• Kubernetes
• Postgres
• Python
• SQL
• Go

Benefits

• Generous benefits
• Fair compensation