Staff / Senior Software Engineer, Agent Engineering

Leoforce; New York (NY); On-site; USD 185,000 - 285,000; Full time

Benefits offered by this job

Equity / ownership

Direct access to founders/CTO

SoHo NYC office

Job summary

Leoforce is seeking a Staff/Senior Software Engineer specializing in Agent Engineering in New York City. The role focuses on advancing the agent runtime powering research, analysis, and action capabilities, with a emphasis on building durable, auditable multi-agent systems.

You will drive production-grade agent orchestration, memory, and model-runtime engineering across providers, ensuring secure, scalable, and observable operation in a fast-moving startup environment.

Qualifications

• Experience shipping production LLM or agent systems beyond prototypes.
• Ability to diagnose nondeterministic failures and separate model judgment from deterministic software.
• Experience with long-running, multi-agent orchestration.

Responsibilities

• Own and advance the platform's agent runtime and foundational systems.
• Build infrastructure for long-running agent work with visibility and steerability.
• Design and build the tool and action framework used by agents.
• Connect agents to retrieval and knowledge systems; ensure grounding in evidence.
• Improve persistent memory and context-management for complex workflows.
• Strengthen evaluation, tracing, and release processes for agent behavior.
• Improve quality and reliability while managing latency, cost, security, and risk.

Skills

Stateful multi-agent workflows

Tooling & contracts

Agent memory

Model routing

Observability & security

Job description

Staff / Senior Software Engineer, Agent Engineering

6939646

Date Posted: 10-03-2026

Job Description

Experience: Senior Level

Salary: $185,000 - $285,000 per year

Job Details

The Mission

We are seeking a Staff/Senior Software Engineer specializing in Agent Engineering to advance the agent runtime powering our platform's research, analysis, and action capabilities.

Our agents must be capable of decomposing open-ended objectives, retrieving trustworthy evidence, safely using tools, coordinating long-running work, and producing high-fidelity outputs that remain traceable to their sources.

• Execution state and orchestration
• Tool use and permissions
• Context and persistent memory
• Model routing
• Failure recovery
• Evaluation and observability
• Security and operational controls

The goal is to enable agents to perform meaningful work over extended periods without losing context, exceeding their authority, silently failing, or producing unsupported conclusions.

You will also advance the platform's reasoning and memory layer, enabling agents to accumulate knowledge, recognize changes, resolve contradictions, and maintain direct source context across workflows.

What We're Looking For

We're looking for an experienced engineer who has shipped production LLM or agent systems beyond the prototype stage.

You should be comfortable diagnosing nondeterministic failures, establishing clear boundaries between model judgment and deterministic software, and determining when workflows require autonomous execution, human approval, or conventional application logic.

Ideal experience includes

• Production orchestration of stateful, long-running, and multi-agent workflows
• Tool and action infrastructure with strong contracts, permissions, and approval boundaries
• Retrieval, context engineering, evidence management, and persistent agent memory
• Model-runtime engineering across multiple providers, latency profiles, and deployment environments
• Evaluation, tracing, security, and operational control of nondeterministic AI systems
• Designing reliable systems around LLM behavior in production environments

Key Responsibilities

• Own and advance the platform's agent runtime and the foundational systems used to build new agent-driven products.
• Build infrastructure that allows agents to manage long-running work from initial assignment through completion while keeping activity visible, steerable, and connected to relevant projects, people, evidence, deadlines, and deliverables.
• Design and build the tool and action framework agents use to safely interact with internal systems and external services.
• Connect agents to retrieval and knowledge systems so reasoning, memory, citations, and generated artifacts remain grounded in authoritative evidence.
• Build and improve persistent memory and context-management systems for complex, multi-step agent workflows.
• Strengthen evaluation, tracing, simulation, and release processes for agent behavior.
• Improve agent quality and reliability while managing latency, inference cost, security, and operational risk.
• Diagnose and resolve complex production failures involving nondeterministic AI systems.

Nice to Have

• Experience deploying agent systems in government, defense, legal, healthcare, financial services, or other highly regulated environments
• Familiarity with policy or legal research where temporal accuracy, provenance, and citation precision are critical
• Experience operating self-hosted or multi-provider inference in restricted environments
• Experience building agents that create durable artifacts or perform permissioned actions on behalf of users
• Experience designing secure AI systems involving human-in-the-loop approvals and authorization boundaries

Working Here

This is a full-time, in-person position in SoHo, New York City, with team members expected to work from the office five days per week when not deployed with customers.

Certain customer engagements may require background checks, security reviews, access approvals, or eligibility for a U.S. government security clearance. Some projects may also be subject to U.S. citizenship or other customer-specific access requirements.

We're looking for driven builders who want to create systems from the ground up and push the boundaries of agentic AI, natural language understanding, document intelligence, reasoning, and personalized relevance.

This is a fast-moving startup environment with ambitious goals and significant ownership. It is not a conventional 9-to-5 role. Flexibility may be required during critical deployments, customer incidents, product launches, and other company-critical periods.

In return, this position offers substantial technical ownership, direct access to consequential customers and institutions, and the opportunity to build AI systems that influence how important decisions and work get done.

How We Work

• Own outcomes, not just tasks. Identify what needs to happen and drive it through completion.
• Move quickly without lowering the standard. Speed and rigor should reinforce one another.
• Stay close to the mission and the user. The best technical decisions start with understanding the real problem.
• Work across boundaries. Everyone contributes beyond the narrow limits of their job title.
• Communicate directly. We value clear thinking, candid feedback, and low-ego collaboration.
• Build for the real world. Our systems must perform reliably in complex, regulated, and high-stakes environments.

A bit about us

We are building a new kind of technology company focused on solving complex, high-impact problems, beginning with the way organizations interact with government.

Government influences nearly every consequential market, yet the infrastructure connecting public institutions and private organizations remains fragmented, manual, and difficult to navigate. Our mission is to rebuild that interaction layer.

Our core platform provides organizations with the intelligence they need to understand what government is doing, why it matters, and what actions to take next. From that foundation, we design and deploy secure, mission-specific systems for government agencies, enterprises, and institutions operating in complex and highly regulated environments.

We combine frontier AI, deep public-sector expertise, and forward-deployed execution. Our team includes experienced leaders and engineers from major technology companies and senior government organizations. We are backed by leading institutional investors and trusted by organizations working on high-stakes challenges across government and industry.

Why join us

• Equity / ownership — meaningful upside if the company grows.
• Direct access to founders and CTO — this particular role reports directly to the CTO and works with the founding team.
• Very high technical ownership — owning core agent-runtime infrastructure rather than maintaining a small component of a mature product.
• Frontier agentic-AI work — production agents, long-running workflows, memory, retrieval, model routing, tool use, evaluation and security rather than simply wrapping an LLM API.
• Early-stage impact — engineers joining now can materially influence architecture, engineering standards and product direction.
• Strong founding team — leadership backgrounds include the White House, State Department, Datadog and Microsoft.
• Funded startup — Helios publicly references a $4M seed round, giving you a concrete funding story when discussing the opportunity.
• Interesting customer/mission exposure — the company is building AI systems for government, policy, procurement and other complex/high-stakes environments.
• SoHo / NYC office — attractive for someone who specifically wants an in-person startup environment and direct collaboration.

#techservices #python #distributed-systems #observability #ai-security #rag #agentic-ai #ai-agents #multi-agent-systems #llm-engineering #llm-orchestration #retrieval #context-engineering #agent-memory #tool-calling #model-routing #llm-evaluation #tier3