Staff/Senior Software Engineer, Hybrid IR and Systems
AI summary of the role
Staff/Senior software engineer to own the retrieval stack of Helios' Proxi platform, including hybrid search, temporal modeling, and permission-aware retrieval over hundreds of terabytes of government and regulated data.
What you’ll do
- Own Proxi's retrieval stack end to end, from corpus onboarding and index design through hybrid retrieval, fusion, reranking, reindexing, and backfills.
- Advance query-understanding and temporal-retrieval capabilities, including intent detection, entity resolution, structured filtering, and jurisdiction-, date-, and version-aware search.
- Improve retrieval performance, reliability, and cost through capacity planning, caching, reranker optimization, and safe degradation under load.
- Expand federated search across Proxi's separate data collections, including source-aware query planning, filtering, score calibration, and result merging.
What you’ll bring
- Expertise in retrieval mechanisms and their complementarity, including lexical (BM25, analyzers, tokenization) and vector (HNSW, quantization) search.
- Experience with rank fusion, score normalization, learning to rank, cross-encoder reranking, duplicate suppression, and source coverage limits.
- Proficiency in query intent classification, entity linking, alias/acronym graphs, and translating natural language into structured filters.
- Knowledge of temporal modeling (valid vs. transaction time, supersession, corrections) and permission-aware retrieval (tenant isolation, PII filtering).
Technologies
BM25 · HNSW · vector search · hybrid retrieval · rank fusion · learning to rank · cross-encoder reranking · entity linking · temporal modeling · federated search
Source and classification
Internal deployment & tooling · Evidence for this classification:
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
More from the job description
Staff/Senior Software Engineer, Hybrid IR and Systems New York City | Full-time | On-site in SoHo, five days per week Reports to the CTO and works directly with the founding team 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 memo [... source excerpt omitted ...] aware retrieval, including tenant isolation, PII filtering and cache key authorizations. Relevance evaluation under sparse labels. Multilingual and cross lingual retrieval. KEY RESPONSIBILITIES Own Proxi’s retrieval stack end to end, from corpus onboarding and index design through hybrid retrieval, fusion, reranking, reindexing, and backfills. Advance our query-understanding and temporal-retrieval capabilities, including intent detection, entity resolution, structured filtering, and jurisdiction-, date-, and version-aware search. Improve retrieval performance, reliability, and cost through capacity planning, caching, reranker optimization, and safe degradation under load. Expan [... source excerpt omitted ...] ionships they concern. Expand support for multimodal content searchable through the same retrieval interface as Proxi’s continuously ingested datasets. Own relevance quality and production performance, including evaluation, indexing, observability, authorization, provenance, and recovery. NICE TO HAVE Domain adaptation of embedding models through fine tuning, hard negative mining or distillation. Work on policy, legislative, procurement, legal or healthcare corpora, where traceable information systems are mandatory. Experience with transliteration and identifying entity names that should never be translated. Operating search in classified, air gapped or forward deployed envi
Employer postings · Data from · Sources