Staff Software Engineer, Search Systems - Code Data

Responsibilities

• Own the architecture of code search and retrieval systems end to end, including hybrid retrieval with dense code embeddings and BM25, candidate generation, ranking, and re-ranking.
• Identify similar code tasks based on code structure, semantics, intent, and difficulty.
• Build systems that select code-specific models and route tasks to the right model.
• Design natural-language-to-query translation for precise search over code and tasks.
• Design and operate indexing pipelines supporting continuous task, solution, and result ingestion.
• Balance incremental updates, full rebuilds, and real-time ingestion.
• Optimize search speed and cost through embedding dimensionality, quantization, ANN index selection, caching, sharding, and serving infrastructure.
• Build evaluation harnesses for evolving embeddings, models, and search quality, including re-embedding, A/B testing, and regression prevention.
• Define technical strategy for code retrieval and lead high-stakes design reviews.
• Establish offline and online evaluation metrics and quality guardrails.
• Prototype critical systems, ship production code, and resolve difficult retrieval and infrastructure problems.
• Mentor engineers through design reviews, pairing, and technical writing.
• Partner with product, research, and engineering leadership on platform investments, build-versus-buy decisions, and technical hiring.

Requirements

• 8+ years of professional software engineering experience, including 3+ years at Senior level or above, with a Staff-level record of organization-wide technical impact.
• Hands-on expertise building search and retrieval systems using dense-embedding retrieval, lexical scoring, hybrid ranking, and re-ranking.
• Strong understanding of search algorithms and index internals, including vector/ANN indices, inverted indices, and search engines or vector databases.
• Experience with HNSW, IVF, product quantization, Elasticsearch, OpenSearch, Lucene, FAISS, or vector databases.
• Experience making cost-versus-speed tradeoffs for high-QPS systems, including latency, throughput, memory, and infrastructure spend.
• Familiarity with translating natural-language questions into structured search queries through query understanding, semantic parsing, or LLM-assisted query generation.
• Excellent distributed-systems, data-modeling, and API-design fundamentals.
• Demonstrated technical leadership and mentorship.
• Fluency with modern AI development tools such as Claude Code, Cursor, or Copilot.
• Excellent communication, ownership, pragmatism, and execution skills.

Nice to Have

• Experience with code search, code understanding, code embeddings, or code-specific models.
• Experience training or fine-tuning code-embedding models or code-specific LLMs.
• Experience with learning-to-rank, semantic search, or recommendation systems in production.
• Familiarity with LLM-based retrieval, RAG patterns, and model routing or selection.
• Experience operating latency-critical services on cloud and orchestration infrastructure.

Compensation and Benefits

• Salary: $250,000–$500,000 per year.
• Generous equity grant vested over four years.
• Up to $15,000 relocation bonus when moving to the Bay Area.
• $10,000 housing bonus for living within 0.5 miles of the office.
• $1,500 monthly meal stipend.
• Free Equinox membership.
• Health insurance.