Backend Software Engineer - AI Lab

About Epiq AI Labs

Epiq AI Labs is the innovation and engineering hub behind Epiq’s next-generation AI platform for corporate legal departments and global law firms. We operate as a startup within a global organization, focused on agentic AI systems, knowledge-driven reasoning, and enterprise-scale simulations.

We are:

• Fast, experimental, and product-obsessed

• Highly collaborative, low-bureaucracy, and deeply technical

• Backed by the resources, data access, and distribution scale of a global ALSP

We are building foundational AI systems, intelligent agents, reasoning engines, knowledge bases, and structured workflows that transform how litigation, investigations, compliance, and corporate knowledge work get done.

Our culture is that of a startup: high autonomy, high trust, rapid iteration, and a team that genuinely enjoys working together.

About the Role

You will build and operate the backend services behind our AI-driven legal platform, including asynchronous processing, data pipelines, APIs, data access, and authentication and authorization.

This role is well suited for an engineer who has built scalable production backend systems and has experience integrating AI/ML or LLM capabilities into real-world applications.

You will own systems end to end, from technical design and implementation through deployment, monitoring, optimization, and ongoing production support.

Scalability and reliability are core requirements. Services should handle growth in tenants, data volume, and concurrency, tolerate partial failures through retry, idempotency, and graceful degradation, and provide the observability needed to diagnose production behavior.

Key Responsibilities

• Design, build, test, and operate scalable backend services and APIs supporting our agentic AI platform

• Build and maintain asynchronous and event-driven processing, including retry, idempotency, dead-letter processing, and failure recovery

• Develop data pipelines that ingest, process, store, and index large volumes of documents and structured data

• Build reliable API integrations and workflows connecting AI systems with enterprise applications and services

• Implement authentication and authorization using OAuth2, OIDC, and SAML, including role-based access control for multi-tenant environments

• Design and optimize PostgreSQL schemas and queries and support schema migrations in production

• Integrate search and vector storage technologies such as Solr and Qdrant

• Instrument services using metrics, logs, traces, and production monitoring

• Write automated tests, participate in code reviews, and maintain continuous integration pipelines

• Contribute to technical design documents and architecture/design reviews

• Collaborate closely with AI engineers, backend engineers, product management, and security stakeholders

• Diagnose performance and reliability issues and optimize services for production scale

Required Qualifications

• 5+ years of professional software engineering experience building and operating backend services in production

• Strong proficiency in Python, or strong experience in a comparable language with the ability to work primarily in Python

• Experience building scalable, distributed, or high-throughput production systems

• Experience with at least one major cloud platform such as AWS, GCP, or Azure

• Hands-on experience building or integrating production AI/ML systems, such as LLM-powered applications, agentic systems, recommendation/ranking systems, retrieval systems, or real-time ML inference

• Experience designing and implementing REST APIs consumed by other services or applications

• Experience with asynchronous or event-driven processing using message queues, task workers, or comparable technologies

• Working knowledge of relational databases, including schema design and query optimization; PostgreSQL experience preferred

• Experience with automated testing and continuous integration practices

• Familiarity with Docker and containerized application deployment; exposure to Kubernetes

• Familiarity with production observability, including metrics, logging, tracing, and monitoring

• Demonstrated proficiency using AI tools in software development

• Strong written and verbal communication skills with the ability to work effectively in an engineering environment where requirements may evolve

Preferred Qualifications

• Experience building LLM, agentic AI, RAG, tool-calling, or AI-powered workflow applications

• Experience with high-volume data or document-processing pipelines

• Experience deploying or optimizing ML inference in production environments

• Experience with search, semantic search, vector databases, or retrieval systems

• Experience with infrastructure-as-code tools such as Terraform

• Experience with multi-tenant SaaS architectures

• Experience with authentication and authorization standards such as OAuth2, OIDC, and SAML

• Experience in legal technology or another regulated industry

• Experience with MLOps, model evaluation, monitoring, or production ML infrastructure

Technology Stack

Python · PostgreSQL · RabbitMQ · Solr · Qdrant · OAuth2 / OIDC / SAML · Azure · Kubernetes · Docker · Terraform · Prometheus · Grafana · OpenTelemetry