Software Engineer, AI Agents

Epiq Company; New York (NY); Hybrid; USD 180,000 - 285,000; Full time

Job summary

Epiq eDiscovery Solutions, Inc. is seeking a Software Engineer to build agentic systems for the AI platform, handling orchestration, reasoning, and evaluation at scale.

You will own components from design to production, ensuring correctness, traceability, and secure tenancy for legal workloads. You will work on retrieval-augmented generation, hybrid search over legal corpora, and integration with in-house model services for classification, extraction, and embeddings.

Qualifications

• 3+ years of professional software-engineering experience with backend, distributed, or AI systems.

Responsibilities

• Design the agentic platform: orchestration of single agents and parallel sub-agents, durable state and memory across long-running jobs, MCP-based tool integration, and trace-level observability.

Skills

LLM-powered apps

Python

System design

Observability

Agent workflows

Retrieval-augmented

Evaluation datasets

Production readiness

Communication

Tools

Prometheus

Grafana

OpenTelemetry

Kubernetes

Docker

PostgreSQL

Solr

Qdrant

Job description

Software Engineer, AI Agents### Software Engineer, AI AgentsApply: Hybrid: Work in Office Part-Time: New York, NY: Full time: Posted Today: R0035438At **Epiq**, your work contributes to complex, global legal outcomes. You’ll join a values‐driven community where integrity guides decisions, **relentless service** sets the bar, and we **thrive on big challenges** together. We invest in your growth with enterprise‐wide learning and mobility. We celebrate who you are, and we respect life beyond work with flexibility that’s recognized externally. Enabled by modern platforms and AI, **you’ll do the most meaningful work of your career** and see your impact at scale.**Job Description:**Epiq AI Labs is the innovation and engineering hub behind Epiq’s next-generation AI platform for corporate legal departments and global law firms. Operating with the speed and autonomy of a startup and the resources of a global alternative legal services provider, the team builds intelligent agents, reasoning engines, knowledge systems, and structured workflows for litigation, investigations, compliance, and corporate knowledge work. We are fast, experimental, and product-obsessed, with high autonomy, high trust, and low bureaucracy. We ship to real legal clients and hold a high bar for correctness, and we use AI tools throughout our own development workflow. The team is deeply technical, highly collaborative, and owns its systems end to end — you design it, you build it, you ship it. ## The OpportunityYou will build the agentic systems at the center of Epiq AI Labs’ legal AI platform, including the orchestration runtime used by other teams, the retrieval layer agents reason over, and the evaluation infrastructure used to measure quality. You will own systems from initial design through production operation.Legal workflows require a high standard of correctness, traceability, confidentiality, and tenant isolation. You will establish the primitives for orchestration, grounded retrieval, and measurable quality that other engineering teams will build on. ## Essential Job Responsibilities* Design the agentic platform: orchestration of single agents and parallel sub-agents, durable state and memory across long-running jobs, MCP-based tool integration, and trace-level observability.* Build the safety layer agents run inside: tool registration and permissioning, sandboxing, guardrails and output validation, and defenses against prompt injection from retrieved content.* Build agent workflows with multi-step reasoning, tool use, human-in-the-loop checkpoints, and recovery from partial failure during long-running execution.* Evaluate developments in model capabilities, agent-design patterns, and evaluation practices, and translate them into platform architecture.* Design retrieval-augmented generation systems with hybrid search over legal corpora and citation grounding to specific sources.* Own and evolve the in-house model services behind classification, extraction, and embeddings — including customer-trained custom models with active learning — and integrate them alongside frontier models.* Build model-level and end-to-end evaluation datasets, benchmarks, and regression checks for classification, extraction, retrieval, and agent workflows. Work with legal domain experts to turn real workflows, corrections, and failure cases into quality improvements, with automated evaluation in CI and monitoring of quality, latency, and cost in production.* Establish LLMOps practices for running models reliably in production: model routing and fallbacks, latency and cost budgets, prompt and context versioning, caching, and quality and reliability monitoring.* Use AI coding agents throughout development while owning the outcome — the design, specifications and test plans, code review, and verification of correctness, security, and maintainability — and ship major changes behind automated tests and controlled rollouts, with product and legal-domain validation where appropriate.* Build scalable backend services and APIs, produce technical design documentation, and partner with product, research, and security stakeholders.* Participate in the on-call rotation; diagnose and resolve production incidents affecting model and agent services, and turn findings into durable fixes.* **Senior+ level:** Define the foundational architecture for running LLM-powered applications and agents reliably in production across teams, and lead the most complex cross-cutting initiatives, including migrations and addressing architectural debt and systemic risks.* **Senior+ level:** Raise the engineering bar by promoting best engineering practice, building reusable platform primitives, mentoring engineers, and partnering with product and engineering leaders on technical direction while staying hands-on and accountable for delivering working software.## Required Qualifications* 3+ years of professional software-engineering experience with demonstrated depth in backend, distributed, or AI systems. Hiring level will reflect demonstrated technical depth, scope of ownership, and impact.* Experience delivering and operating LLM-powered applications in production at scale — beyond prototypes or proofs of concept — including evaluating quality and diagnosing failures.* Experience building tool-using agent workflows or retrieval-augmented generation systems.* Strong production-level proficiency in Python.* Working understanding of the ML lifecycle, including evaluation data, model and dataset versioning, production deployment, and monitoring model quality, with the ability to collaborate with researchers on reliable model updates.* Experience designing evaluation datasets and benchmarks and measuring agent task completion, citation correctness, policy adherence, latency, and cost.* Experience designing services and APIs consumed by other engineering teams.* Experience with observability tooling such as Prometheus, Grafana, or OpenTelemetry.* Strong system-design and architecture experience, including production of technical design documents.* Excellent written and verbal communication, including the ability to work effectively with non-technical domain experts and stakeholders.* Demonstrated proficiency using AI coding agents in day-to-day development, with sound judgment about where they accelerate work and where they fail.* Self-motivated, with high ownership: you solve problems end to end, actively keep up with new developments in AI, and quickly learn and apply new technologies and approaches to your work, including areas you haven't worked in before.* **Senior+ level:** Demonstrated technical leadership at the corresponding level, with a track record of delivering complex distributed systems across multiple teams, and deep expertise in Python, distributed-systems fundamentals, and event-driven architectures.* **Senior+ level:** Proven ability to lead technical direction across organizational boundaries without direct authority, and to communicate architectural trade-offs to technical and non-technical audiences.## Preferred Qualifications* Experience training, fine-tuning, or adapting models to domain-specific tasks, including classification and extraction models and active-learning loops.* Experience building or contributing to public or domain-specific benchmarks for LLMs or agents.* Experience with large-scale data pipelines or document-processing systems.* Experience with multi-tenant SaaS architectures and data-isolation requirements.* Experience in a startup or scale-up engineering environment.* Experience in legal technology, enterprise workflow, or knowledge-management systems.*Candidates who meet most, but not all, of the qualifications above are encouraged to apply.*# LI-KS1 #1100 Epiq eDiscovery Solutions, Inc. ## Technology StackPython · LLM APIs and agent frameworks (Anthropic via Amazon Bedrock, Azure OpenAI, in-house models) · Model Context Protocol (MCP) · Qdrant · Solr · PostgreSQL · RabbitMQ · Azure · Kubernetes · Docker · Prometheus · Grafana · OpenTelemetry The Compensation range for this role is $180,000 -$285,000 USD annually and may be eligible for an annual bonus. **In compliance with federal law, all persons hired will be required to verify identity and eligibility to work in the United States and to complete the required employment eligibility verification form upon hire.** **Must be authorized to work in the United States for any employer.**Your specific salary will be determined based on several factors:* **Location-based market rate** for the role* **Your abilities** in relation to the job specification* **Performance** during screening and interview* **Pay parity** with the wider team in the considered locationFurther details about the package will be provided during the initial screening call with the Talent Acquisition Team.Click here to learn about Epiq's Benefits.