Match score not available

Software Engineer – Search and RAG

Remote:

Full Remote

Contract:

Full time

Experience:

Mid-level (2-5 years)

Work from:

United Kingdom, Canada, United States, Latin America

Offer summary

Qualifications:

Strong Python programming experience., BS in Computer Science or related field., Minimum 4 years of experience in information retrieval., Experience with cloud deployment technologies..

Key responsabilities:

Develop RAG pipelines for data research.
Design algorithms for complex workflows.

HopHR Information Technology & Services Startup https://hophr.com/

11 - 50 Employees

See all jobs

Job description

Our client is a NYC-based fintech company specializing in a platform for alternative investments, including hedge funds, private equity, real estate, and digital assets. Their mission is to democratize access to these opportunities, empowering independent financial advisors and wealth management firms.

Impact

• Build next-generation AI search for alternative asset management.

• Influence product vision discussions.

• Create robust, core frameworks for adoption across products.

Responsibilities:

Develop RAG pipelines to deliver a combination of capabilities to research structured and unstructured data.

Design and develop algorithms to strategically prompt LLMs for complex agentic RAG workflows and chains.

Fine tune RAG pipeline for accuracy, completeness and relevance.

Write high quality, modular code to capture agentic design patterns into reusable and maintainable code.

Create rapid prototypes for user demos and feedback.

Implement a system to evaluate agents using a combination of custom and vendor products.

Create carefully crafted end-to-end and unit test-cases for agents and related subcomponents. • Prepare structured and unstructured data for RAG.

Deploy RAG pipelines on cloud keeping latency and scalability in mind.

Monitor the Generative AI research and tool space and adapt to evolving techniques for optimal LLM use.

Requirements:

Strong Python programming experience.

In-depth understanding of data structure and algorithms.

Understanding of retrieval augmented generation (RAG) and related topics such as chunking strategies, hybrid indexing, graph RAG and agentic RAG.

Experience fine tuning search or RAG with ElasticSearch, Weaviate or similar hybrid search products.

Prompt engineering experience with an intuitive grasp of LLM behaviour and understanding of patterns such as ReACT, CoT, function calling and routing.

Experience with open-source frameworks such as LangChain and LlamaIndex.

Generative AI/LLM test-case and validation experience.

Understanding of cloud deployment such as Kubernetes, Docker and/or cloud ML platforms such as Amazon bedrock.

Exceptional attention to code quality and emphasis on adhering to established software design patterns.

Minimum 4 years of experience in information retrieval and search relevance in a production system.

Experience in related SaaS product development is a huge plus.

BS in Computer Science or a related field.