Staff/Senior Software Engineer, Agent Engineering

New York City | Full-time | On-site in SoHo, five days per week

Reports to the CTO and works directly with the founding team

Advance the agent runtime that powers Proxi's research, analysis, and action capabilities. Our agents must decompose open-ended objectives, retrieve trustworthy evidence, use tools safely, coordinate long-running work, and produce high fidelity outputs that remain traceable to their sources.

At Helios you will own the systems that make agent behavior reliable in production, including execution state, tool use, context, memory, model routing, recovery, evaluation, and security - improving Proxi's ability to perform meaningful work over hours without losing context, exceeding their authority, silently failing, or producing unsupported conclusions.

You will also advance the reasoning and memory layer built on top of the Helios Rapid Ontology System (H.R.O.S.), enabling agents to accumulate knowledge, recognize change, resolve contradictions and carry direct source context across workflows.

We are looking for a senior engineer who has shipped production LLM or agent systems beyond the prototype stage. You should be comfortable diagnosing nondeterministic failures, enforcing boundaries between model judgment and deterministic software and deciding when a workflow requires autonomy, human approval, or conventional application logic.

Expected areas of expertise:

• Production orchestration for 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 providers, latency profiles, and deployment environments.
• Evaluation, tracing, security, and operational control of nondeterministic systems.

KEY RESPONSIBILITIES

• Own Proxi's agent runtime and strengthen foundations for building new agent-driven products.
• Build the systems that allow agents to own long-running work from assignment through completion. Agent activity should remain visible, steerable, and connected to the relevant project, people, evidence, deadlines, and deliverables in Action Rail.
• Build the tool and action framework agents use to interact with internal systems and external services safely.
• Connect agents to Proxi's retrieval and knowledge systems so reasoning, memory, citations, and generated artifacts remain grounded in authoritative evidence.
• Improve the evaluation and release discipline for agent behavior, traces and simulations to improve quality while controlling latency, cost, and risk.

NICE TO HAVE

• Experience deploying agent systems in government, defense, legal, healthcare, or other regulated environments.
• Familiarity with policy and legal research where temporal accuracy, provenance, and citation precision are essential.
• Experience operating self-hosted or multi-provider inference in restricted environments.
• Experience building agents that create durable artifacts or perform permissioned actions on a user's behalf.

WORKING AT HELIOS

This is a full-time, in-person role based in our SoHo office in New York City. Team members are expected to work from the office five days per week when they are 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 be subject to U.S. citizenship or other customer-specific access requirements.

We're not looking for passengers; we want driven innovators with a hunger to build from the ground up - obsessed with pushing the boundaries of natural language understanding, document processing, and personalized relevance.

Helios is a fast-moving startup with ambitious goals. This is not a conventional 9-to-5 role. We expect flexibility during critical deployment periods, customer incidents, product launches, and other company-critical work. In return, this role offers unusual ownership, direct access to consequential institutions, and the opportunity to build systems that affect how major decisions are made.

HOW WE WORK

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