Software Engineer (AI / LLMs)

APIPHANI, INC.
Boston, MA, United States
5 days ago
Apply on www.juju.com
Prepare application

Role details

Contract type
Permanent contract
Employment type
Full-time (> 32 hours)
Experience level
Expert
Experience required
6 years minimum
Compensation
$120,000.0 - $160,000.0
Working hours
Regular working hours
Job source

Tech stack

Clean Code Principles Application Programming Interfaces (APIs) Artificial Intelligence Amazon Web Services Amazon S3 Cloud Computing Cloud Engineering Code Review Continuous Integration Data Security DevOps Distributed Systems
+26 more
Github Information Technology Operations Python (Programming Language) PostgreSQL Open Source Technology Search Technologies SQL Databases Systems Integration TypeScript Datadog AWS Cdk Retrieval-Augmented Generation Large Language Models Multi-Agent Systems Generative AI Backend Event Driven Architecture Infrastructure Automation Frameworks Machine Learning Operations Virtual Agents Cloudwatch Terraform Dynatrace Automation Anywhere Docker Microservices

Job description

Apiphani is building the future of intelligent infrastructure automation through agentic AI. We’re looking for a Senior Backend Engineer to help design and build the systems that power Luumen - an AI-driven automation platform used by enterprise IT and managed service providers around the world.

This is a high-impact, zero-to-one engineering role focused on building the backend foundations for large-scale AI orchestration. You’ll 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 the 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

Requirements

  • 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 like embeddings, similarity search, and retrieval-augmented generation

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

  • 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 asynchronously in a distributed team

  • Strong sense of ownership 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

  • Interest in shaping how AI is applied to real-world IT operations

Benefits & conditions

Base Salary $120,000-$160,000 USD Company Benefits*

  • Medical/dental/vision - 100% paid for employees, 50% paid for dependents
  • Life and disability - 100% paid for employees
  • 401K - 3% contribution, no employee contribution necessary
  • Education and tuition reimbursement
  • Accident, critical illness, hospital indemnity benefits offered through our providers
  • Employee Assistance Program
  • Legal assistance
  • Paid Time Off - up to 6 weeks per year
  • Sick Leave - up to 2 weeks per year
  • Parental Leave - up to 12 weeks

*Benefits listed in the job description apply to employees working in the United States. For international employees, Apiphani partners with an Employer of Record, Deel, and provides all statutory benefits required under local law; certain U.S.-specific programs (such as EAP, legal assistance, etc.) may not be available outside the United States. The specific benefits package will be outlined in the local employment agreement issued through Deel.

About the company

Apiphani is a technology-enabled managed services company dedicated to redefining what it means to support mission-critical enterprise workloads. We’re a small but rapidly growing company, which means there’s lots of room for growth and learning opportunities abound!

Apiphani is dedicated to creating a diverse and inclusive work environment for all as a fundamental component of our business. Diversity and inclusion are the bedrock of creativity and innovation. Without diversity of experience and thought, we would fail to progress as a company and as a team. Apiphani strives to foster an environment of belonging, where every employee feels respected, valued, and empowered. We embrace the unique experiences, perspective, and cultural background, which only you can bring to the table.

Apply for this position

This job is hosted externally. Click below to view the full posting and apply.

Apply on www.juju.com
Prepare application

Good distractions

Talks and stories from around this role — technically off-topic, practically not.

2:08 min

Essential engineering roles in the generative AI space

Mary Grygleski Mary Grygleski · LIVE

2:07 min

Inspecting default bridge architectures and custom Docker networks

Oliver Seitz Oliver Seitz · World Congress 2025

6:36 min

Funding open source through GitHub Accelerator and Sponsors

Stormy Peters · World Congress 2023

2:17 min

Mapping the maturity roadmap for scaled devops adoption

Dominik Krichbaum Dominik Krichbaum · World Congress 2026 Europe

2:14 min

Exploring internal AI product initiatives and global engineering roles

Maria Apazoglou · Coffee With Developers

2:34 min

Docker sandbox architecture and microVM environment integration

Manuel de la Peña Manuel de la Peña · World Congress 2026 Europe

Videos

See all

Related articles

See all