U

Unusual Ventures

Invests in early-stage tech startups

Staff/Senior Software Engineer - Agent Engineering, Helios

AI Application EngineeringConfirmed live in the last 24 hours
Full-timeNew York, NY, USANo salary listed

About the Job

Requirements

  • Experience shipping production large language model or agent systems beyond the prototype stage.
  • Ability to diagnose nondeterministic failures and distinguish model judgment from deterministic software.
  • Ability to determine when workflows require autonomy, human approval, or conventional application logic.
  • Experience with production orchestration for stateful, long-running, and multi-agent workflows.
  • Experience with tool and action infrastructure, including contracts, permissions, and approval boundaries.
  • Experience with retrieval, context engineering, evidence management, and persistent agent memory.
  • Experience with model-runtime engineering across providers, latency profiles, and deployment environments.
  • Experience with evaluation, tracing, security, and operational control of nondeterministic systems.

Responsibilities

  • Own Proxi’s agent runtime and strengthen the foundations for building new agent-driven products.
  • Build systems that allow agents to manage long-running work from assignment through completion while remaining visible, steerable, and connected to relevant projects, people, evidence, deadlines, and deliverables in Action Rail.
  • Build the tool and action framework agents use to interact safely with internal systems and external services.
  • Connect agents to Proxi’s retrieval and knowledge systems so reasoning, memory, citations, and generated artifacts remain grounded in authoritative evidence.
  • Improve evaluation and release discipline for agent behavior, traces, and simulations while controlling quality, latency, cost, and risk.
  • Advance the reasoning and memory layer built on the Helios Rapid Ontology System to help agents accumulate knowledge, recognize change, resolve contradictions, and carry direct source context across workflows.

Desired Qualifications

  • 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.

About the Company

Unusual Ventures

Invests in early-stage tech startups

Unusual Ventures is a venture-capital firm that backs early-stage tech startups and helps them reach product-market fit. It combines financial investment with practical support, offering portfolio companies access to a Field Guide—a library of more than 100 articles, case studies, interviews, and tools designed to guide founders through building and growing a business. The company earns returns by taking equity stakes in its investments and helping portfolio companies grow value. Its differentiator is the integrated mix of capital with structured, tactical resources and guidance that goes beyond standard funding, specifically aimed at accelerating product-market fit and business growth for startups.

Company size
11-50
Company stage
Not listed
Total funding
$3B
Headquarters
Menlo Park, CA
Founded
2018

Recently Posted Jobs

Explore more opportunities at Unusual Ventures

See more jobs