Generative AI Engineer

About Us: At Bytebricks, we are at the forefront of the AI revolution, building intelligent, large-scale systems that redefine what's possible. We don't just use technology; we architect the future of it. We are seeking a brilliant and highly skilled LLM Engineer with 1-2 years of professional experience who is passionate about building the complex backend systems required to power cutting-edge generative AI applications. If you are driven to solve intricate problems and build robust, scalable AI solutions from the ground up, we want to hear from you.Please note: This is not an entry-level position. We are seeking candidates with demonstrated professional experience, and applications from fresh graduates will not be considered.What You'll Do:As an LLM Engineer, you will be the architect behind our most innovative AI features, responsible for the entire lifecycle of our generative AI solutions, from model integration to the underlying infrastructure.Architect Advanced AI Systems:  Design, develop, and deploy sophisticated LLM-powered applications, including complex multi-agent workflows.Build and Optimize RAG Pipelines:  Engineer and fine-tune state-of-the-art Retrieval-Augmented Generation (RAG) systems using vector databases like Pinecone to create highly contextual and multi-modal AI experiences.Deploy and Fine-Tune Language Models:  Manage the deployment and continuous optimization of various LLMs (including models from OpenAI, Claude, Groq, and open-source alternatives) on hosted Linux virtual machines, ensuring low latency and high throughput.Engineer Core Backend Infrastructure:  Build the robust, scalable backend that our AI depends on. This includes designing and implementing secure REST APIs using Python (FastAPI, Django), managing authentication (JWTs, sessions), and ensuring system reliability.Optimize Data and Performance:  Manage and optimize relational databases (PostgreSQL, MySQL) and leverage in-memory caching with Redis to ensure our AI systems are highly responsive and performant under load.Develop Real-Time Voice AI:  Construct high-performance, low-latency pipelines for Text-to-Speech (TTS) and Speech-to-Text (STT) to enable seamless real-time conversational AI.What We're Looking For:Core AI/LLM Expertise:A MUST:  Deep, hands-on experience designing and building complex, multi-agent systems using frameworks such as  LangGraph . Experience with CrewAI or OpenAI Swarms is a major advantage.Proven expertise in architecting and optimizing RAG systems and deep familiarity with vector databases (e.g., Pinecone).Demonstrable experience with LLM orchestration frameworks like LangChain.Practical experience fine-tuning and deploying LLMs on custom infrastructure, with a strong focus on performance and scalability.A solid understanding of multi-modality in AI systems.Essential Backend & DevOps Foundation:1-2 years of professional experience  with advanced proficiency in Python and modern backend frameworks, particularly FastAPI (Django/Flask experience is a plus).Strong proficiency with  Docker  for containerization and experience deploying and managing  cloud-based microservices architectures .Hands-on experience with  CI/CD pipelines , including writing deployment scripts for major cloud platforms ( Azure, AWS, GCP ).Proficiency with the complete software development lifecycle:  development -> QA feedback -> development -> QA Approval -> production .Solid experience building, securing, and scaling RESTful APIs and a deep understanding of authentication patterns (e.g., JWTs).Strong command of relational databases (PostgreSQL, MySQL) and extensive experience with Redis for high-performance caching.Soft Skills:Ability to thrive in a  fast-paced, results-oriented work environment .A collaborative mindset with a proven ability to work effectively in a distributed team.Exceptional problem-solving skills, with a focus on creating scalable, high-performance solutions.A relentless passion for learning and staying at the frontier of artificial intelligence.Why Join Us?Pioneering Projects:  Work on genuinely innovative projects that leverage the absolute latest in AI and backend technology.Deep Technical Challenges:  Solve complex, meaningful problems that will push your skills to the limit.Flexibility & Autonomy:  Enjoy the freedom of remote work and the autonomy to architect solutions your way.Growth & Development:  Be part of a culture that invests in continuous learning and professional growth.Competitive Compensation:  We offer a top-tier salary and benefits package that recognizes and rewards your expertise.