Vector DB Engineer

Client Name: SANS

End Client Name: TechTransient Point72 Asset Management

Job Title: Vector DB Engineer

Location: New York, NY (Local to NY/NJ only)

Work Type: Hybrid

Job Type: Contract

Rate: $65/hour on C2C

LinkedIn needed

Notes:

• Must be okay with an onsite interview round.

Job Description:
The Vector DB Engineer will be responsible for designing, developing, and maintaining high-performance vector database systems to support LLM-backed applications. This role will collaborate with AI/ML engineers, data scientists, and product teams to build scalable, secure, and optimized solutions in the financial services domain.

Roles and Responsibilities:

• Design, develop, and maintain vector database systems (e.g., Pinecone, Weaviate, Milvus, FAISS, Qdrant).
• Integrate LLMs (OpenAI, Claude, LLaMA, etc.) into data pipelines and AI solutions using RAG and embedding-based retrieval.
• Build and manage embedding pipelines (OpenAI, Hugging Face, Sentence Transformers, etc.) for structured/unstructured data.
• Optimize vector search for latency, relevance, and scalability across large datasets.
• Collaborate with ML/AI engineers, data scientists, and product teams on end-to-end AI-powered solutions.
• Monitor system performance, ensure data security, and maintain availability.
• Evaluate/experiment with vector indexing techniques (HNSW, IVF, PQ) and distance metrics (cosine, Euclidean, dot-product).
• Stay current with advancements in LLMs, vector databases, and semantic search.

Required Skills:

• Proven hands-on experience with vector databases (e.g., Pinecone, Weaviate, Milvus, FAISS, Qdrant).
• Strong understanding of LLMs and embedding-based retrieval (OpenAI, Claude, LLaMA, etc.).
• Experience building embedding pipelines with tools like Hugging Face and Sentence Transformers.
• Expertise in vector search optimization for scalability and latency.
• Knowledge of indexing techniques (HNSW, IVF, PQ) and distance metrics.
• Strong collaboration skills across engineering, data, and product teams.

• Prior experience in the financial services or hedge fund domain.
• Familiarity with monitoring tools, data security, and compliance in regulated industries.
• Experience with semantic search and AI-driven knowledge systems.