Mid Level AI Developer - Remote - 3 Months - Octopus by RTG - Immediate Hir

robusta

2d•Remote

About The Position

We're looking for a Mid Level AI Developer to design, build and run production-grade agentic AI systems on AWS and Azure. You'll turn business problems into reliable multi-step agent workflows that use LLMs, tools and enterprise data. You'll own solutions from architecture and prototyping through deployment, evaluation and monitoring, and you'll set engineering standards for how we build with AI. The role includes designing and building single- and multi-agent workflows; developing LLM applications on AWS and Azure; building retrieval-augmented generation pipelines; integrating agents with internal systems, APIs and SaaS tools; implementing evaluation frameworks and responsible-AI controls; and deploying and operating services with CI/CD, infrastructure as code and observability. You will optimize performance, reliability and cost, mentor engineers, conduct design and code reviews, document architectures and decisions, and collaborate with product owners, data teams, security and architecture to take AI use cases from idea to production.

Requirements

Bachelor's degree in Computer Science, Engineering or a related field, or equivalent experience.
3+ years of software engineering experience, including 1+ years building LLM or GenAI applications in production.
Strong Python skills and experience building and operating APIs and services.
Hands-on experience building agentic systems with a modern framework, such as LangGraph, LangChain, Microsoft Agent Framework / Semantic Kernel, AutoGen, Strands Agents or CrewAI.
Production experience with at least one of AWS or Azure AI services, and working knowledge of the other.
Practical RAG experience with vector databases or search services such as OpenSearch, Azure AI Search, pgvector or Pinecone.
Experience with cloud fundamentals, including containers, networking, identity (IAM / Entra ID) and secrets management.
Experience with CI/CD, Git and infrastructure as code such as Terraform, Bicep or CloudFormation.
Understanding of LLM evaluation, prompt engineering, and AI-specific safety and security risks.
Strong communication skills and ability to explain trade-offs to technical and non-technical stakeholders.

Nice To Haves

Experience with MCP servers, multi-agent protocols such as A2A, or agent orchestration at scale.
Fine-tuning or model customization experience, and experience with open-source models.
Background in a regulated sector such as banking, healthcare or government.
Cloud certifications such as AWS Certified AI Practitioner or Solutions Architect, Azure AI-102 or AZ-204, or AZ-400.
Experience with data engineering technologies such as Spark, Databricks, Fabric or Glue, and data governance.

Responsibilities

Design and build single- and multi-agent AI workflows with planning, tool use, memory and human-in-the-loop controls.
Develop LLM applications on AWS and Azure, and recommend appropriate platforms and models for use cases.
Build RAG pipelines covering data ingestion, chunking, embeddings, vector search and grounding over enterprise data.
Integrate agents with internal systems, APIs and SaaS tools using standards such as MCP and function/tool calling.
Implement evaluation frameworks for quality, accuracy, safety and cost, including regression tests, LLM-as-judge methods and human review.
Implement guardrails and responsible-AI controls, including prompt-injection defenses, content filtering, PII handling, access control and audit logging.
Containerize and deploy services using CI/CD and infrastructure as code, and implement observability such as tracing, logging, latency and token-cost monitoring.
Optimize performance, reliability and cost across models, prompts and infrastructure.
Mentor engineers, conduct design and code reviews, and document architectures and decisions.
Work with product owners, data teams, security and architecture to take AI use cases from idea to production.