Applied AI Engineer

Lumbra•New York, NY

3d•$150,000 - $300,000•Onsite

About The Position

Lumbra is hiring an Applied AI Engineer to build and ship production AI features for Nebula, its agentic harness used by analysts across the Intelligence Community and Department of Defense. The role focuses on agent behaviors, retrieval, tool integrations, and analyst-facing product surfaces, with evaluation and production reliability built into the development process. It is an onsite position in New York City and is not eligible for remote or hybrid work. The role is structured around approximately 60% building, 25% evaluating and iterating, and 15% incorporating feedback from classified deployments. The engineer will develop the agent loop and execution runtime, evaluation harnesses, and retrieval and orchestration architecture. They will work with Forward Deployed Engineers and Deployment Strategists to convert field learnings into product improvements, and will build vendor-neutral features that work across model providers, including models available on classified networks. This is a product engineering role rather than a research-, prompt-only, or demo-focused role. Features are expected to be production software that analysts rely on, with their effectiveness demonstrated through evaluation. The engineer will work alongside CIA officers, MIT engineers, Special Operations combat veterans, and applied AI engineers from frontier labs. The role offers ownership of part of an early-stage company and work that affects national security.

Requirements

At least 2 years of professional software engineering experience shipping production code; candidates with 4 or more years may be considered at the senior level.
Strong Python skills.
Experience shipping at least one LLM-powered feature to real users and explaining how its effectiveness was evaluated, including the evaluation, metric, and resulting changes.
Hands-on experience with at least one of retrieval pipelines, tool use and function calling, or agent orchestration.
Experience designing evaluations for non-deterministic output and iterating on prompts, retrieval, and tooling based on failures.
Strong software fundamentals, including testing, code review, typed interfaces, and writing code that can withstand constant change.
Ability to turn a loosely defined request into a working feature without a fully specified ticket.
Strong fundamentals in scalable distributed systems, service-oriented architectures, networking, and systems design; ideally, experience owning both the technical vision and execution of a foundational platform system end to end.
Proficiency in Python, Go, Rust, or a similar systems language.
Experience with cloud infrastructure such as GCP, AWS, or Azure, and container orchestration such as Kubernetes.
Ability to take full ownership of work from design through deployment and operations.
Ability to navigate ambiguity and make sound technical decisions independently, ideally in both 0-to-1 and more mature team or company settings.
Willingness to work onsite in New York City.

Nice To Haves

Experience with evaluations, agents, or retrieval pipelines at scale.
Experience with Model Context Protocol or similar tool-use frameworks.
Experience with open-weight models, self-hosted inference, or constrained compute environments.
Experience with graph databases or vector search for knowledge representation and retrieval.
Enough TypeScript and React experience to build the UI for shipped features.
Exposure to intelligence analysis, OSINT, or other analytical workflows.
Eligibility to obtain a U.S. security clearance.

Responsibilities

Build AI features end to end, from prototype through production, including agent behaviors, retrieval, tool use, and analyst-facing interfaces.
Create evaluation datasets, graders, and regression suites to measure feature quality and detect capability regressions.
Analyze failures and iterate on prompts, context, retrieval, and tooling based on evidence.
Ensure production quality for model calls, including latency, cost, error handling, fallbacks, and observability.
Build vendor-neutral features that work across model providers, including models available on classified networks.
Work with Forward Deployed Engineers and Deployment Strategists to turn feedback from classified deployments into product fixes.
Build and scale the agent loop and execution runtime for model requests, tool execution, long-running sessions, and context updates.
Develop automated benchmarking pipelines and evaluation suites that stress-test accuracy, latency, context-window limits, and regressions.
Build reliable retrieval-augmented generation frameworks and orchestration layers for high-throughput, low-latency AI features.
Own work from design through deployment and operations.

Benefits

Health, dental, and vision insurance, with 99% of employee premiums and 100% of dependent premiums covered.
Optional HSA plan that is lower-premium, HSA-eligible, fully portable, and self-directed or managed.
Health Reimbursement Account for qualified healthcare expenses.
Company-paid $150,000 life insurance plus AD&D coverage.
401(k) with a 100% match on the first 6%, immediately vested with no cliff or waiting period.
Fully covered Wellhub Gold membership, including access to gyms and fitness studios.
Unlimited PTO.
Federal holidays and additional paid days off over winter break.
Supportive leave of absence program, including time off for military service, medical events, and parental leave.
Breakfast, lunch, and snacks in the office.
Pre-tax commuter benefits.
Company-paid phone plan and iPhone.