About Helios
Helios is building a new kind of company to solve America’s hardest problems, starting with the government interaction layer.
Government shapes every consequential market, but the infrastructure connecting public institutions and private organizations remains fragmented, manual, and difficult to navigate. Helios is rebuilding that layer.
Our core platform, Proxi, gives organizations the intelligence they need to understand what government is doing, why it matters, and what to do 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 bring together frontier AI, deep public-sector expertise, and forward-deployed execution. Our team includes leaders and builders from the White House, U.S. Department of State, Datadog, and Microsoft. We are backed by leading institutional investors and trusted by organizations working on high-stakes problems across government and industry.
Mission
As a search and information retrieval engineer at Helios, you will own the key components of the Helios Rapid Ontology System (H.R.O.S.), our long horizon temporal memory management and search system. This system is what powers Proxi’s lossless memory system, enabling traceable and auditable AI outputs for sensitive information environments. This also is used to power retrieval over our several hundred terabyte data corpora. Expected areas of expertise:
- Retrieval mechanisms and their complementarity.
- Analyzers, tokenization, field boosts and BM25 parameterization for lexical indices. HNSW parameters, quantization, shard design and recall against latency for vector indices.
- Rank fusion, score normalization, learning to rank, cross encoder reranking, duplicate suppression and source coverage limits.
- Query intent classification, entity linking, alias and acronym graphs, controlled expansion and translation of natural language into structured filters and facets.
- Temporal modeling, valid vs. transaction time, supersession, corrections and effective date intervals.
- Permission aware retrieval, including tenant isolation, PII filtering and cache key authorizations.
- Relevance evaluation under sparse labels.
- Multilingual and cross lingual retrieval.
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.