Logo
BTI Solutions

GEN AI Software Engineer

BTI Solutions, Ridgefield Park, New Jersey, us, 07660


Why work with us?

Proven people.

Everyone on our team has earned a CPC (Certified Personnel Consultant) or CTS (Certified Temporary Staffing Specialist) accreditation from the National Association of Personnel Services. We are experts at staffing and recruiting with more than 16 years of experience serving employers.

Proven process.

Our approach to staffing isn't just a little bit different; it's a whole different ball game. While most staffing firms emphasize transactional services (taking and filling job orders), BTI Solutions focuses on providing more strategic solutions.

By acting as workforce consultants, we are able to find innovative and intelligent strategies for improving productivity, meeting project deadlines, improving hiring quality, decreasing turnover, and reducing total labor costs.

Our recruiting and candidate assessment process assures the highest quality matches between job seeker and employer, so you will get people who not only have the right qualifications but who also have the appropriate personality fit for your organization.

Proven results.

More than anything, the biggest difference with BTI Solutions is the one that matters most: bottom-line results.95% client satisfaction rate

- measures client satisfaction vs. expectations.Our

clients have worked with us for over 10 years , on average.BTI Solutions counts

4 Global Telecommunication companies as clients.Client referrals

are BTI Solutions'

largest source of new clients.Google Review 4.4, Facebook Review 4.8GEN AI Software EngineerGeneral Description:

POSITION SUMMARY

We're seeking a skilled engineer to lead the development of cutting-edge RAG applications using state-of-the-art LLM technologies. The ideal candidate will have a strong background in AI and NLP, with hands-on experience in building and optimizing LLM-based systems. This role requires expertise in integrating LLM solutions via APIs with both third-party tools and in-house applications. Experience with AWS Bedrock is highly valued, and familiarity with microservices architecture in cloud environments is a significant plus.

Essential Responsibilities:

MAIN TASKS AND DUTIES

Design and implement RAG (Retrieval-Augmented Generation) systemsIntegrate and optimize Large Language Models (LLMs) via APIsDevelop efficient information retrieval and extraction systemsBuild and manage databases and vector storesApply Natural Language Processing (NLP) techniquesMonitor performance and continuously improve systemsIntegrate LLM solutions with other third-party tools and in-house applicationsDesign and implement APIs for seamless integration of LLM capabilitiesMust Have the Following Competencies:

SKILL AND TASKS REQUIRED

Preferred Qualifications:

Contributions to open-source LLM projectsExperience building AI systems in large-scale production environmentsExperience with vector databases (e.g., Pinecone, Faiss)Proficiency with relevant libraries such as Transformers, Hugging FaceExperience with AWS Bedrock for AI/ML model deployment and managementExperience with microservices architecture (MSA) in cloud environmentsFamiliarity with LLM API providers (e.g., OpenAI, Anthropic, Cohere)Supervisory Requirements:

WILL THIS POSITION SUPERVISE, OR NO?

No

Requirements:

EDUCATION AND EXPERIENCE

Bachelor's degree or higher in Computer Science, Artificial Intelligence, or related field (Master's preferred)Proficiency in Python programmingDeep understanding of LLMs, RAG systems, and API integrationExperience with NLP and machine learningStrong skills in database and API developmentKnowledge of distributed systems and cloud computingExpertise in integrating AI models with various software solutionsSuggested Tech Stack:

Language: PythonFrameworks: PyTorch or TensorFlow, FastAPI or Flask for API developmentDatabases: PostgreSQL, MySQL, MongoDB,Vector Stores: Pinecone, FaissCloud Platforms: AWS (including Bedrock), Google Cloud, or AzureIntegration Tools: Apache Kafka, RabbitMQ