Senior Software Engineer (AI / LLMs)

Our client is a technology-enabled managed services company dedicated to redefining what it means to support mission-critical enterprise workloads. They are a small but rapidly growing organization, offering significant opportunities for growth and continuous learning.

Our client is committed to fostering a diverse and inclusive work environment as a fundamental component of their business. They believe diversity and inclusion are the bedrock of creativity and innovation. By embracing unique experiences, perspectives, and cultural backgrounds, they strive to create an environment where every team member feels respected, valued, and empowered.

Senior Software Engineer — Agentic AI Platform

Location: Remote
Employment Type: Full-time
Compensation: Competitive

Our client is building the future of intelligent infrastructure automation through agentic AI. They are seeking a Senior Backend Engineer to help design and build the systems that power an AI-driven automation platform used by enterprise IT teams and managed service providers worldwide.

This is a high-impact, zero-to-one engineering role focused on building backend foundations for large-scale AI orchestration. You will work on distributed systems that combine traditional infrastructure automation with large language models (LLMs), retrieval-augmented generation (RAG), and intelligent agents.

What You’ll Do

• Design and implement backend services that enable intelligent agent workflows and autonomous infrastructure actions

• Develop APIs and orchestration layers in Python and TypeScript, integrating LLMs, vector databases, and observability pipelines

• Build scalable systems to support LLM-based reasoning, retrieval, and decision-making across cloud infrastructure

• Integrate with AWS Bedrock and other LLM platforms to support multi-model capabilities

• Develop data access and semantic search layers using vector databases (e.g., pgvector, Pinecone, Qdrant)

• Build robust monitoring, testing, and CI/CD systems to ensure reliability and reproducibility of AI workflows

• Collaborate closely with Product and DevOps teams to design architecture diagrams, plan deployments, and monitor system health

• Write clean, maintainable code with clear documentation and strong adherence to security and performance best practices

• Participate in code reviews, design discussions, and iterative delivery cycles to improve product velocity and quality

What We’re Looking For

• 6+ years of backend engineering experience in production environments

• Strong proficiency in Python and TypeScript for building distributed, event-driven systems

• Deep understanding of AWS services (Lambda, ECS, Bedrock, S3, CloudWatch, etc.)

• Experience designing APIs, microservices, and event pipelines that interface with LLMs or AI models

• Familiarity with vector databases and concepts such as embeddings, similarity search, and retrieval-augmented generation

• Experience with infrastructure-as-code tools such as Terraform or AWS CDK

• Strong understanding of SQL and schema migration workflows (PostgreSQL or similar)

• Hands-on experience with Docker, GitHub Actions, and cloud-native CI/CD workflows

• Ability to diagram systems, communicate architecture decisions clearly, and work effectively in a distributed team

• Strong ownership mindset and ability to deliver in fast-moving, ambiguous environments

Bonus Points

• Experience working with LangChain, OpenAI, or Anthropic APIs

• Familiarity with agentic frameworks or AI orchestration systems

• Background in observability or APM tooling (e.g., Datadog, Dynatrace)

• Prior experience building automation or infrastructure management tools

• Contributions to open-source LLM or MLOps projects

• In